cslt Wiki - 用户贡献 [zh-cn]

2025-11-10

2025-11-10T09:00:58Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Primary School handbook, grad 5 done
* AI Graph pictures review
||
*
||
*
|-

|-
|Lantian Li
||
* Review AI Book – High School Edition (Done).
* Prepare defense for my Professor title
* Prepare ICCIP keynote.
||
*
||
*
|-

|-
|Ying Shi
||
* prepare for interview
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* Draft v0.0 of the MT-HuBERT paper after ICASSP26 (Done), need to add several experiments.
** Evaluating the performance of MT-HuBERT on other SUPERB tasks(in training)
** Conducting SS and SD experiments with different numbers of mixed speakers.
** Cross-validation of single- and multi-talker ASR performance.
||
*
||
*
|-

|-
|Xiaolou Li
||
* Some cncvs documents
* PhD application documents
||
*
||
*
|-

|-
|Zehua Liu
||
*study for civil servant and interview
||
*
||
*
|-

|-
|Pengqi Li
||
* Draft of the paper and investigate some related paper.
* AI course of Tsinghua University Middle School.
||
*
||
*
|-

|-
|Wan Lin
||
* Helping to design training strategy and experiments for MD tasks
* Current results from weixiong [https://z1et6d3xtb.feishu.cn/docx/EZCzdMqwlo3SuhxJXqDcAOa9n8b?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
* AED with Softmax+CE training for sound separation ranking [https://z1et6d3xtb.feishu.cn/docx/HEmjduO75oaZJDxPPLXcQZ9zntv]
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Finished reading all COLM & NeurIPS 2025 MAS papers (26/26); currently summarizing.
||
*
||
*
|-

|-
|Jiaying Wang
||
* modify the loudness rank biased sepatation paper
||
*
||
*
|-

|-
|Yu Zhang
||
* NeurIPS 2025 MAS paper reading (residual papers after Chen Junhui’s selection; will share some this Friday)
* Deploy AIGE website
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
* Some finetune experiments with real mispronunciation data [https://z1et6d3xtb.feishu.cn/docx/EZCzdMqwlo3SuhxJXqDcAOa9n8b]
||
*
||
*
|-

|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
* Performance benchmarks on rk3576 for ONNX-CPU, RKNN-fp16 and RKNN-int8.
** Vision models: YoloV5.
** Audio models: CED, speech-enroll KWS (in progress).
* SpEx Android demo (in progress).
||
*
||
*
|-

|-
|Lily
||
* New office setup
* AIGE & AIRadiance dailywork
||
*
||
*
|-

2025-11-03

2025-11-03T10:35:26Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* paper sharing.
* the resources checking for the middle-school AI course(20/20).
* rewrite MT-HuBERT paper.
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Draft of the paper(60%)
* AI course of Tsinghua University Middle School
* Check the PPT(10/20)(will complete tonight)
||
*
||
*
|-

|-
|Wan Lin
||
* Design the experiments for mispronunciation detection
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Reading papers from COLM & NIPS 2025 (17/26)
* Summarize the recent development trajectory of multi-agent systems and integrate it with my own ideas
||
*
||
*
|-

|-
|Jiaying Wang
||
* mid-term report
||
*
||
*
|-

|-
|Yu Zhang
||
* AED Project thing
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Yue Gu
||
* prepare for the job writing test
||
*
||
*
|-
|-
|Qi Qu
||
* Big progress in debugging the heap corruption in elderly alarm customization. Still some minor bugs yet to be located.
* Some server maintenance work.
||
*
||
*
|-

2025-10-27

2025-10-27T10:55:03Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||

* AI handbook for primary schools, 4th grad.
* Talk in middle school of Renmin Middle School.

||
*
||
*
|-

|-
|Lantian Li
||
* Review AI Book – College Edition (52/53).
* Organize teaching course materials.
* Guide BUPT-STU's proposal and mid-term reports.
* Project: HUAWEI Phase I Delivery Report and FENYINTA AVSD Schedule
||
* Proofread my MLA Book.
* Review AI Book – High School Edition.
||
*
|-

|-
|Ying Shi
||
* prepare for interview
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Midreport
* APSIPA 2025
||
*
||
*
|-

|-
|Junming Yuan
||
* check the resources for the middle-school AI course(16/20)
* paper reading
||
*
||
*
|-

|-
|Xiaolou Li
||
* Mid-term framework and report
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Conduct supplementary experiments and write the paper
* AI course of Tsinghua University Middle School
* Review the practical manual(v2) again（Liuzhou high school and Xian Gongshang）. I think is good enough.
* Check the PPT(5/10)
||
* Paper(v1)
||
*
|-

|-
|Wan Lin
||
* Phd application
* MD task
** Reproduce previous framework in shiyin's code: work normally
** Prepare for similar phoneme pronunciation replacement
* NC's report
||
*
||
*
|-

|-
|Tianhao Wang
||
* mid-term framework & report
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* train of attractor-based speech separation
** the training loss is normal, but the training is too slow. I plan to change the current code from Chainer version to PyTorch version
* Proposal framework and report
||
*
||
*
|-

|-
|Junhui Chen
||
* LLM:
** finish Baseline & Reflexion metric collection (without analysis yet)
** continue reading papers from COLM & NIPS 2025 (9/26)
** proposal discussing with @ZhangYu
||
*
||
*
|-

|-
|Jiaying Wang
||
* A Loudness-Perceptual-Biased Speech Separation Method paper modification
* mid-term report
||
*
||
*
|-

|-
|Yu Zhang
||
* AED: add provided VPU hard case for training
** With a 2-second window length during training and testing, "WYL-type cough" can be effectively solved;
** With a 0.6-second window length, adding new training data yields only a minor improvement.
* LLM:
** finish Baseline & Reflexion metric collection (without analysis yet)
** proposal discussing with @chenjunhui
* AI2S webset deploy
||
*
||
*
|-

|-
|Wenqiang Du
||
* Check PPT for primary/middle/high school
* Writing project documents with Weiman Sun
||
*
||
*
|-

|-
|Yang Wei
||
* Reproduce shiying's experiment on LibriSpeech (train/test: random data aug; ROC AUC 0.99)
* Training with other data aug method: replace a word with similar pronunciation from lexicon. (under training)
||
*
||
*
|-

|-
|Yue Gu
||
* job hunting and Phd thesis
* Mispronunciation task: 1 use ChatGPT to generate the negtive samples with similar pronunciation, 2 compute the similar matrix between speech embeddings and phone embeddings, then conduct dynamic programming algorithm on it to find the maximum cumulative-similarity path. The mispronunciations will corresponding to a lower similar scores.
||
*
||
*
|-
|-
|Qi Qu
||
* Debugging for elderly alarm customization: possible heap corruption.
* Experiments w/ RKNN toolkit.
||
*
||
*
|-

|-
|Lily
||
* Paper reading
* Check AI textbook 2nd semester, primary school version (3 grad)
* AIGE & AIRadiance dailywork
||
*
||
*
|-

2025-10-13

2025-10-13T10:58:37Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI book (primary) English version done
* AI textbook (2nd semester) Grad 3 (1/2)

||
*
||
*
|-

|-
|Lantian Li
||
* Review AI Book — College Edition (34/53).
* My professional title evaluation (1/2).
* Proposal for audio scene detection.
||
*
||
*
|-

|-
|Ying Shi
||
* submitted resumes to many companies
* prepared for interviews
* conducted some preliminary experiments on MD tasks
||
*
*
||
*
|-

|-
|Zhenghai You
||
* SS 3-5mix benchmark for Huawei Project
* Multi-Step Infer[https://z1et6d3xtb.feishu.cn/docx/LlgjdMYVbocGD1xjkMSc17Ttnke]
** Multi-task-search can keep reference metrics on 2-mix data while improving non reference metrics
** However, on noisy data, our method is not effective, maybe the quality of speech extraction is too poor, exceeding threshold to improve
||
*
||
*
|-

|-
|Junming Yuan
||
* Further evaluation of our MT-HuBERT model on 2 speech generation downstream tasks(SS & SE).
** Result in [https://z1et6d3xtb.feishu.cn/docx/SihydfjgZo8b0txhRtickebdnwc]
||
*
||
*
|-

|-
|Xiaolou Li
||
* avhubert pretraining iter3 and finetune test
* orgnize collected data
* do some prepare for NCMMSC2025
||
*
||
*
|-

|-
|Zehua Liu
||
* LLM to Generate topics as context For midterm thesis
* stuff about CNVSRC2025
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* Experiments for memory and reasoning [https://z1et6d3xtb.feishu.cn/wiki/NJLtw3l1Xi2xQBkUpCbcRic9nOh?from=from_copylink]
* Start reviewing and reproducing weixiong's code
||
*
||
*
|-

|-
|Tianhao Wang
||
* writing my paper
* add a multi-modal query baseline
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* paper sharing
* prepare the code of attractor-based speech separation, the model is in training
||
*
||
*
|-

|-
|Junhui Chen
||
* collect more novel reflection method metrics for analysis
* paper reading about LM swarm
||
*
||
*
|-

|-
|Jiaying Wang
||
* separation training
** 3mix cc and cc-order use loud data
** 4mix pit and pit-order use loud data
** 2-5mix cc training code finished
* spk model
** change structure to ResNet34 (wait to train)
||
*
||
*
|-

|-
|Yu Zhang
||
* paper reading and prepare for paper sharing
* AED: add pitch dim training & test (no significant improvement)
||
*
||
*
|-

|-
|Wenqiang Du
||
* Check english version AI primary handbook
* Dealing with our company accounting issues
||
*
||
*
|-

|-
|Yang Wei
||
* Debug training problem of MD model on TIMIT
||
*
||
*
|-

|-
|Yue Gu
||
* submit resume and prepare for the job interview
* SPL paper revision and proof
* my PhD thesis
||
*
||
*
|-
|-
|Qi Qu
||
* Misc. tech support for Babel Technology.
||
*
||
*
|-

|-
|Lily
||
* Thesis Writing
* AIRadiance dailywork
||
*
||
*
|-

2025-09-29

2025-09-29T10:57:27Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
* Review AI Book — College Edition (12/53).
* Project matters: HUAWEI SS/AutoBGM; FYT A/V GenreDetect.
* Prepare materials for my professional title evaluation.
||
*
||
*
|-

|-
|Ying Shi
||
* Thesis
* revise resume
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Multi-Step Infer （multi-task search）[https://z1et6d3xtb.feishu.cn/docx/LlgjdMYVbocGD1xjkMSc17Ttnke]
* Huawei 4-mix SS model training
||
*
||
*
|-

|-
|Junming Yuan
||
* Grade 8 AI practice handbook(done!)
* Further evaluation of our MT-HuBERT model on other speech downstream tasks.
** Based on SUPERB benchmark(Speech processing Universal Performance Benchmark)
*** Firstly focused on Source Separation downstream task(still in training)
*** Intermediate results(SI-SDRi at 50K training steps): MT-HuBERT: 10.77, HuBERT-BASE: 9.84.
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Science popularization activities in Changzhi, Shanxi, and returned to the lab on tomorrow.
||
*
||
*
|-

|-
|Wan Lin
||
* Writing research proposal
* Some Experiments [https://z1et6d3xtb.feishu.cn/wiki/NJLtw3l1Xi2xQBkUpCbcRic9nOh?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
* writing my paper (method and experiments is almost done)
* job interviews
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* read some papers on speech separation of unknown number of speakers
* Apply EDA(encoder-decoder based attractor calculation) method to speech separation
** Environment Configuration(done)
** Familiar with the code and make some adjustments to it(in progress)
||
*
||
*
|-

|-
|Junhui Chen
||
* LLM:
** 2 different reflection paper reading
** Baseline self-reflection metric collection — code completed, data collection in progress.
** Integrating new reflection methods (e.g. beamsearch-based reflection) into the current pipeline in collaboration with @Zhang Yu — work in progress.
||
*
||
*
|-

|-
|Jiaying Wang
||
* construct loudness training data: librimix with different loudness source
* loudness order exp[https://z1et6d3xtb.feishu.cn/docx/TDQ9dMYiHoyZnLx6xJDcLg1ZnF3]:
** chain based structure: 2mix 11.92(150 epoch)
** convtasnet structure: still training, 60epoch achieve 12.29
* ctc order exp:
** only use ctc for order, chain based structure: 10.65
* a speculation: Compared with semantic information (provided by CTC), acoustic-oriented information may be more suitable as a basis for separation.

||
* try to use speaker info as order
||
*
|-

|-
|Yu Zhang
||
* LLM:
** Baseline self-reflection metric collection — code completed, data collection in progress.
** Integrating new reflection methods (e.g. beamsearch-based reflection) into the current pipeline in collaboration with @chenjunhui — work in progress.
* AED:
** Added humming test and analysis for Huawei.
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
* Train English MD model based on Whisper
||
*
||
*
|-

|-
|Yue Gu
||
* polish the structure of my thesis and continue find jobs
||
*
||
*
|-
|-
|Qi Qu
||
* Elderly alarm customization.
* SLAM (simultaneous localization & mapping) experiments.
||
*
||
*
|-

2025-09-22

2025-09-22T10:58:05Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Travel to Gaungxin
* AI handbook English version (primary) almost done

||
*
||
*
|-

|-
|Lantian Li
||
* Polish the ICASSP 2026 paper
* Discussions on the HUAWEI project
* Graduate recommendation interview
* Review AI Book - College Version (2/53)
||
*
||
*
|-

|-
|Ying Shi
||
* 2 ICASSP Paper
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Mutli-step Infering
** Try to use a pre-train model with different sampling rates（it work）
** Try multi-step infering in DPRNN (it work)
** Reproduce the current Sota TSE model - X-TFgridNet
||
*
||
*
|-

|-
|Junming Yuan
||
* ICASSP26 paper final revise
* Grade 7 AI practice book(Done) and Grade 8 AI practice book(1/10)
||
*
||
*
|-

|-
|Xiaolou Li
||
* Rewrite s2s finetune code with avhubert framework
* Design specific speaker VTS experiment
* PhD application
||
*
||
*
|-

|-
|Zehua Liu
||
*get sick and relax
*read some paper about Visual Speech Recognition
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* permission request for figures in English book
* SFT for knowledge unlearning and context reasoning [https://z1et6d3xtb.feishu.cn/wiki/NJLtw3l1Xi2xQBkUpCbcRic9nOh?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
* ChainSep experiments & paper writing
* job hunting and interviews
* some support work for graduate recommendation
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* Supplement experiments to the paper
* read the paper related to my thesis proposal
||
*
||
*
|-

|-
|Junhui Chen
||
* found a survey about reflection [https://arxiv.org/pdf/2308.03188], plan to flow different ways of reflection in it
* found a self-reflection inference pipline paper [https://arxiv.org/abs/2405.06682], applying its code to help building our code
** Completed the reflection inference pipeline of CK-PLUG mix ReDEeP
* rewriting the inference code to verify whether the performance of ckplug and redeep is consistent in our model (Verification successful)
||
*
||
*
|-

|-
|Jiaying Wang
||
* reproduce sot: use current encoder dosen't work
* use pretrained asr model for separation
** training pure asr module (to determine separation order)
** code done
* reconstructing code (finished in 1-2 days)
||
*
||
*
|-

|-
|Yu Zhang
||
* Completed the reflection inference pipeline of CK-PLUG mix ReDEeP, following a paper [https://arxiv.org/abs/2405.06682]
* Reproduced the experiments from paper using our model (base model: llama-2-7b-hf) to check if there are any bugs, with performance closely matching the reported results.
||
*
||
*
|-

|-
|Wenqiang Du
||
* Primary AI practice book（Completed 3 and 4 grade）
||
*
||
*
|-

|-
|Yang Wei
||
* Keep working on MD experiment.
||
*
||
*
|-

|-
|Yue Gu
||
* working on my thesis and seeking career opportunities.
||
*
||
*
|-
|-
|Qi Qu
||
* Elderly alarm customization.
||
*
||
*
|-

|-
|Lily
||
* Thesis writing
* AIradiance's daily work
||
*
||
*
|-

2025-09-15

2025-09-15T10:53:19Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI handbook English version Check

||
*
||
*
|-

|-
|Lantian Li
||
* Proposal for audio scene understanding.
** Mix-Audio-HuBERT, Mix-Audio-Detector, and Scene-LLM
||
*
||
*
|-

|-
|Ying Shi
||
* mispronunciation detection Paper(introduction & Related work )
* MT-Hubert Paper
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Non-intrusive metrics mutli-step inference[https://z1et6d3xtb.feishu.cn/docx/LlgjdMYVbocGD1xjkMSc17Ttnke]
||
*
||
*
|-

|-
|Junming Yuan
||
* revise icassp paper
* Grade 7 AI practice book(17/17)
||
*
||
*
|-

|-
|Xiaolou Li
||
* Prepare for interview
* PhD Application (RP, PS...)
||
*
||
*
|-

|-
|Zehua Liu
||
*Paper reading and sharing
*job hunting
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* find sources for figures in English book and permission request
* edit code for knowledge unlearning
* phd application
||
*
||
*
|-

|-
|Tianhao Wang
||
* icassp2026 experiments
* job hunting
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* icassp2026 experiments with tianhao
||
*
||
*
|-

|-
|Junhui Chen
||
* finish debugging of ReDeEP CK-PLUG mix transformer with @Zhang Yu, push to github
* read survey about reflection to look for standard evaluation ways
||
*
||
*
|-

|-
|Jiaying Wang
||
* joint training exp and conclusion see[https://z1et6d3xtb.feishu.cn/docx/TDQ9dMYiHoyZnLx6xJDcLg1ZnF3]
* interviews for job
||
*
||
*
|-

|-
|Yu Zhang
||
* AED
** duanci testing: ROC AUC 0.90 (acceptable)
* LLM
** finish debugging of ReDeEP CK-PLUG mix transformer with @chenjunhui
** choose evaluate dataset & writing inference pipeline (still doing)
||
*
||
*
|-

|-
|Wenqiang Du
||
* Prepare my PhD proposal defense
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Yue Gu
||
* job hunting and organizing the structure of my thesis.
||
*
||
*
|-
|-
|Qi Qu
||
* ROS experiments.
* Dev work for elderly alarm customization.
||
*
||
*
|-

|-
|Lily
||
* Thesis writing
* Polishing the AI General Education (Junior high school Edition) Handbook
* Polishing the AI General Education (University Edition) Practical Handbook（实践手册）
||
*
||
*
|-

2025-09-08

2025-09-08T10:55:24Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI textbook college version publish
* AI handbooks English version check

||
*
||
*
|-

|-
|Lantian Li
||
* Comeback
||
*
||
*
|-

|-
|Ying Shi
||
* mispronunciation detection paper
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Modify multi-step inference
** Using spk similarity to reduce extraction confusion
||
*
||
*
|-

|-
|Junming Yuan
||
* ICASSP2026 paper v0.0(done)
* Grade 7 AI practice book(2/30)
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Speaker Verification XAI experiments (to check and conclude)
* Preparation and meeting for the AI course of this term at Tsinghua Middle School
* High-school AI practice book (Volume 1/2)
||
*
||
*
|-

|-
|Wan Lin
||
* Benchmark preparation
* Phd application
* Finding sources and requesting use for figures in English books
||
*
||
*
|-

|-
|Tianhao Wang
||
* submit resume, job exam & interview
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* compared the performance of our models. Overall, the initial architecture（CLAP audio-text) had the best results
* train the soloaudio with AudioSet dataset
||
*
||
*
|-

|-
|Junhui Chen
||
* Reproducing ReDeEP & CK-PLUG
* Reconstructing code of ReDeEP & CK-PLUG
**ReDeEP is done; CK-PLUG is almost done, debugging by @Zhangyu
* Reading paper
||
*
||
*
|-

|-
|Jiaying Wang
||
* data tramsfer and environment settings done
* joint training experiment are training
* plan to generate loudness data
* some interviews
||
*
||
*
|-

|-
|Yu Zhang
||
* AED humming cough duanci data collection & hard sampling training (AUC 0.75 -> 0.96)
* reproducing ReDeEP & CK-PLUG with @chenjunhui
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
* Doing some supplementary experiments for text enroll md paper.
||
*
||
*
|-

|-
|Yue Gu
||
* skim a paper about personal dialogue generation
* collect some information about the job market, polish my resume and prepare for the written job exams
||
*
||
*
|-
|-
|Qi Qu
||
* Wrapped knock detection model in a service and deployed it in production.
* Development for elderly alarm customization.
||
*
||
*
|-

2025-08-11

2025-08-11T10:59:52Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Primary Textbook, first-term 8 books, done.
* English version, AI Graph, checked and submitted.
* College version, half done.

||
*
||
*
|-

|-
|Lantian Li
||
* Carry on ML book (290/326)
* APSIPA paper review
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Some support work for AACC2025
* Paper Reading on Audio LLM and Flow Matching
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*Qwen3-32B（CER：41.78%）> Qwen2.5-32B(CER:43.87%)
*Leetcode and prepare for interview
||
*
||
*
|-

|-
|Pengqi Li
||
* I was on leave last week
||
* Prepare a proposal for ICASSP
||
*
|-

|-
|Wan Lin
||
* Read paper
* Run experiments aboout memory network
||
*
||
*
|-

|-
|Tianhao Wang
||
* demo deployment on huawei server
* review my project for job finding
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* Replaced Clap with CED model(it doesn't work, maybe need further check)
||
*
||
*
|-

|-
|Junhui Chen
||
* back from vacation
* keep on reading paper
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* Huawei AED code organize and DOC writing (delivery to Zhang Hong Cheng)
* Feedback handling for RoyalFlush GongFu Project acceptance
||
*
||
*
|-

|-
|Wenqiang Du
||
* Completed the recording of the AI courses for Jiaoyubu
||
*
||
*
|-

|-
|Yang Wei
||
* Get a better text enroll mispronunciation detection model. (500 hour: recall 14% -> 23%)
||
*
||
*
|-

|-
|Yue Gu
||
* I have finished the first revised version of my SPL paper and the response. I am still focusing on polishing.
||
*
||
*
|-
|-
|Qi Qu
||
* Walking through ROS tutorials.
* Elderly alarm customization: new feature requests (among which, support for Cantonese).
||
*
||
*
|-

2025-07-28

2025-07-28T12:02:58Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
* Write ML book (194/326)
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Support work for AATC2025
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
* Still running exp on CNAVHuBERT (loss drop normally)
* Reading some paper about mm self-supervised work
||
*
||
*
|-

|-
|Zehua Liu
||
*VTS inference Deployment and Submission website design（ready to open on August 1st）
** 21 teams regist the CNVSRC2025
** 12 teams already get the data
*Reading paper and prepare for interview
||
*
||
*
|-

|-
|Pengqi Li
||
* AIGE meeting
||
*
||
*
|-

|-
|Wan Lin
||
* Read papers
* Revised and submitted NS paper to NC
* Run some experiments about sparse network
||
*
||
*
|-

|-
|Tianhao Wang
||
* body uncomfortable, go to the hospital
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
* ASR training
** 3mix & 4mix baseline training
** Share backbone: discuss with shiying, decide to add cnn module after separator of ss branch. Now calculating the audio length after several cnns.
||
*
||
*
|-

|-
|Yu Zhang
||
* Still Refining and bug fix for Technical Investment Strategy
* Paper Reading (Parameter Knowledge & Context Knowledge Conflict)
* Huawei AED additional dataset test (Low SNR Human Speech + KTV Noise / Canteen Noise)
||
*
||
*
|-

|-
|Wenqiang Du
||
* AIGE meeting
||
*
||
*
|-

|-
|Yang Wei
||
* Fix text enroll md training data problem and retrain.
* Got a text enroll kws model with 10k hour. (base and real_keyword_finetune)
||
*
||
*
|-
|Yue Gu
||
* polish my SPL paper (80%). Now, my paper is out-of-length, I must delete some content.
* write the response (20%)
||
*
||
*
|-
|-
|Qi Qu
||
* (In progress) development for customized elderly alarm project.
* Refactoring model/sevice licensing.
||
*
||
*
|-

2025-07-28

2025-07-28T11:37:30Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
* Write ML book (194/326)
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Support work for AATC2025
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*VTS inference Deployment and Submission website design（ready to open on August 1st）
** 21 teams regist the CNVSRC2025
** 12 teams already get the data
*Reading paper and prepare for interview
||
*
||
*
|-

|-
|Pengqi Li
||
* AIGE meeting
||
*
||
*
|-

|-
|Wan Lin
||
* Read papers
* Run some experiments about sparse network
||
*
||
*
|-

|-
|Tianhao Wang
||
* Cervical pain, go to the hospital
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
* ASR training
** 3mix & 4mix baseline training
** Share backbone: discuss with shiying, decide to add cnn module after separator of ss branch. Now calculating the audio length after several cnns.
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* AIGE meeting
||
*
||
*
|-

|-
|Yang Wei
||
* Fix text enroll md training data problem and retrain.
* Got a text enroll kws model with 10k hour. (base and real_keyword_finetune)
||
*
||
*
|-
|Yue Gu
||
* polish my SPL paper (80%). Now, my paper is out-of-length, I must delete some content.
* write the response (20%)
||
*
||
*
|-
|-
|Qi Qu
||
* (In progress) development for customized elderly alarm project.
* Refactoring model/sevice licensing.
||
*
||
*
|-

2025-07-21

2025-07-21T10:54:47Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Thesis
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Some support work for AATC2025
* Reproducing solospeech (the results are not good)
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
* AV-HuBERT training...still need a week to finish the training iter 1
* Paper reading
||
*
||
*
|-

|-
|Zehua Liu
||
*CNVSRC2025 website design(Submission system) and paper reading
*Leetcode and eight-part essay for finding jobs
||
*
||
*
|-

|-
|Pengqi Li
||
* 4.5 days for camp work
* make AI courses for JiaoYuBu（1）
||
*
||
*
|-

|-
|Wan Lin
||
* Read papers
* Reproduce Cannistraci-Hebb for sparse network
||
*
||
*
|-

|-
|Tianhao Wang
||
* experiments for my paper (fail to reproduce FlowSep, diffusion model is hard to train)
* eight-part essay for finding jobs
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Help some latex things about ML book
* Paper reading
||
*
||
*
|-

|-
|Jiaying Wang
||
*GuoChuang competition: First Prize of Beijing
* Chain Separation
** libri2mix cc baseline finished，3/4/5mix training ongoing
** reconstructing ASR module：for better integrate the code into the separation framework
* some leetcode for job hunting
||
*
||
*
|-

|-
|Yu Zhang
||
* Paper reading about LLM knowledge leaking and Knowledge conflicts between LLM’s world knowledge and RAG inputs.
* Integrate a back-testing environment that supports order-matching mechanisms into the HFT trading framework.
* Refine tech policy in Multi Agent Investment (still about the technical factor calculate range)
||
*
||
*
|-

|-
|Wenqiang Du
||Camp work
||
*
||
*
|-

|-
|Yang Wei
||
* Finish training a text enroll mispronunciation detection model, under test.
* Prepare and attend Tencent Camp
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* Response and manuscript is done
* 4.5 days for camp work
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2025-07-14

2025-07-14T10:50:40Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
* Visit EURECOM
* Write ML book (96/326)
||
*
||
*
|-

|-
|Ying Shi
||
* Thesis
* Some HUAWEI project stuff
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Reproducing solospeech (completed training of vae and DiT, currently training Corrector)
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* NS with M=1500: 0.989%EER in Vox1-O
* paper reading
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* trained the new architecture(base version) of sound separation
* prepare the Huawei project meeting
||
*
||
*
|-

|-
|Junhui Chen
||
* Nuclear power plant project
** Some possible problems and suggestions of coding
** Help prepare some acceptance Docs
* Help some latex things about ML book
* Paper reading
||
*
||
*
|-

|-
|Jiaying Wang
||
* GuoChuang Competition finished
||
*
||
*
|-

|-
|Yu Zhang
||
* Label Generate for RoyalFlush (routine pipeline writing, currently is done)
* High frequency trading framework learning and source code reading (based on WonderTrader)
||
*
||
*
|-

|-
|Wenqiang Du
||
* Recording AI courses for JiaoYuBu（8/12）
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* almost complete the response and revised manuscript
* TSinghua & Tencent camp train and PPT
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2025-07-07

2025-07-07T12:35:36Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* thesis
* some discussions with HUAWEI regarding the evaluation criteria of sound separation project.
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Reproduce the VAE of SoloSpeech
||
*
||
*
|-

|-
|Junming Yuan
||
* Middle-school AI Textbook
* revise High-school slides
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*CNVSRC2025 website design and release
*Reading paper
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* Revised paper and submitted
* Exp:
** loaded and fixed 1-layer feature extractor for 8 layer: no improvement
** run 1-layer NS with 1.5k enroll per test
||
*
||
*
|-

|-
|Tianhao Wang
||
*re-run the experiments for my paper
*paper reading about generative sound sep
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* trained the new architecture(base version) of sound separation, but the test results are not very good. It may be because there is too little training data after filtering, so I have added some data from vggsound, the model is in training.
* some test of Huawei project
||
*
||
*
|-

|-
|Junhui Chen
||
* Revise NS paper
* Read nuclear power plant code
* Read paper
||
*
||
*
|-

|-
|Jiaying Wang
||
* ASR training
** Libri2Mix clean data：30epoch LER14.043%， 70epoch LER12.01%（align with shiying）
** Use Libri2Mix noise data still training
||
*
||
*
|-

|-
|Yu Zhang
||
* Label launch work for the acceptance of the RoyalFlush project (mainly SQL coding and HIVE pipeline)
||
*
||
*
|-

|-
|Wenqiang Du
||
* Primary-school AI Textbook
||
*
||
*
|-

|-
|Yang Wei
||
* More attempts to improve mispronounce detection performance by adapting the AM (not work, F1 23% -> 18%)
* Check primary school material
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* polish my journal paper and wirte the response
||
*
||
*
|-
|-
|Qi Qu
||
* Some trivial development work.
||
*
||
*
|-

2025-07-07

2025-07-07T10:45:19Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* thesis
* some discussions with HUAWEI regarding the evaluation criteria of sound separation project.
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* Middle-school AI Textbook
* revise High-school slides
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* Revised paper and submitted
* Exp:
** loaded and fixed 1-layer feature extractor for 8 layer: no improvement
** run 1-layer NS with 1.5k enroll per test
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* Label launch work for the acceptance of the RoyalFlush project (mainly SQL coding and HIVE pipeline)
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* polish my journal paper and wirte the response
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2025-06-30

2025-06-30T10:25:14Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
* CNVSRC2025 Baseline
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* Supply experiments for paper
* Run some experiments(self att mask for test in multi-layer and leverage 1-layer feature extractor for 8-layer)
* Paper: Revision parts mentioned are nearly finished, need further check
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Finished Hainan teaching assistant work
* Continue revising NS paper
* Read paper
||
*
||
*
|-

|-
|Jiaying Wang
||
* GuoChuang Competition
** modify slides v2 and verbatim transcript
** LingAn bank account already opened
* Prepare Libri2Mix - Libri5Mix for ASR
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* almost finish th supplement of experiments
* rewriting a section to make it more clear
||
*
||
*
|-
|-
|Qi Qu
||
* (Continuous) integrating PJSIP to ESP32-based application.
* Experiment: Text-Enroll KWS + FunASR [https://b30lttjm7l.feishu.cn/docx/OsJOdIf6ToRDkVxKg7XcbdwKnSJ?from=from_copylink].
||
*
||
*
|-

2025-06-23

2025-06-23T10:53:34Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
* Write ML book (38/326)
* Go on Hainan D&B Course
* BUPT Graduate matters
||
*
||
*
|-

|-
|Ying Shi
||
* Write introduction of my thesis
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* Optimize ASR code(MT-HuBERT WER: 11.33%->7.39%)
* JiaoYuBu AI lesson
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*CNVSRC2025 VTS part Baseline code rewriting and checking （Finish）and uploading to github
||
*
||
*
|-

|-
|Pengqi Li
||
* XAI paper-writing the draft.
* JiaoYuBu AI lessons
* TsingHua middle school AI class summer school prepare(Sunday)
||
*
||
*
|-

|-
|Wan Lin
||
* supply experiments for ns paper
||
*
||
*
|-

|-
|Tianhao Wang
||
* Huawei project things
* huawei competition baseline data preparing
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Hainan D&B Course teaching assistant
* Help do some ML book things
* Read paper
||
*
||
*
|-

|-
|Jiaying Wang
||
* GuoChuang competition：
** Slides template modification
** Bussiness Plan completed
* ASR training
** remix max 8k and 16k data, can train model after final check
||
*
||
*
|-

|-
|Yu Zhang
||
* Hainan D&B Course teaching assistant
* AED Quant bug fix (model preparing related)
* Refine Technical Analysis policy for multi agent investment
||
*
||
*
|-

|-
|Wenqiang Du
||
*Check and record AI courses from Jiaoyubu (4/12)
||
*
||
*
|-

|-
|Yang Wei
||
* Did experiment about mispronunciation detection about unclear pronunciation. Adaptation experiment is in progress.
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* supplement a baseline and some alation experiments
* revise my paper
||
*
||
*
|-
|-
|Qi Qu
||
* (Continuous) integrating PJSIP to ESP32-based application.
* Extended analysis based on on-device test results of Text-Enroll KWS + FunASR.
||
*
||
*
|-

2025-06-16

2025-06-16T10:57:40Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Redesign AI textbook for primary school
* Travel to Hefei

||
*
||
*
|-

|-
|Lantian Li
||
* Submit the Teaching Reform Proposal at BUPT (Speech Information Processing)
* Revise NS Paper
* Kick off Hainan Database Course
||
*
||
*
|-

|-
|Ying Shi
||
* Restructure my thesis
* Start writing my thesis
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Real scenario sample testing and badcase analysis for Huawei
||
*
||
*
|-

|-
|Junming Yuan
||
* some MT-HuBERT extended exp[https://z1et6d3xtb.feishu.cn/docx/Azkwd9VrVosk26xtoZ8cbBnuntc]
* JiaoYuBu AI lessons with Qiang bro.
||
*
||
*
|-

|-
|Xiaolou Li
||
* optimize GA project ppt, demo, model
* attend GA project mid-term presentation
* paper reading
||
*
||
*
|-

|-
|Zehua Liu
||
*Document and PPT work for GA midterm presentation
*Rewrite code for CNVSRC2025 VTS Baseline
||
*
||
*
|-

|-
|Pengqi Li
||
* XAI paper
** Summarize some experimental phenomena
** organize the structure of the paper
** start writing the draft.
* JiaoYuBu AI lessons with Qiang bro.
||
*
||
*
|-

|-
|Wan Lin
||
* paper reading
* NS
** 3-layer transformer: worse than 1-layer
** Memory bank for enrollment: paired enrollments: 200->512, EER in clean:1.05%->0.99%
||
*
||
*
|-

|-
|Tianhao Wang
||
* prepare CET6
* reproducing FlowSep (a generative based sound sep model)
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* some test for Huawei project
||
*
||
*
|-

|-
|Junhui Chen
||
* read paper
* do PhD transfer things, prepare review
* revise NS paper
||
*
||
*
|-

|-
|Jiaying Wang
||
* GuoChuang Competition
** slides modification and change template
** business plan first version completed
* ASR training
** regenerate wsj0 2mix data (dealing with chenjunhui)
||
*
||
*
|-

|-
|Yu Zhang
||
* add Passive Reflection query (to stabilize the backtesting process)
* some quant model training for Huawei AED
||
*
||
*
|-

|-
|Wenqiang Du
||
* JiaoYuBu AI lessons whit junming and pengqi (4/12)
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* polish my SPL paper and submit it
* modify my TASLP paper according to the reviews' recommendation
||
*
||
*
|-
|-
|Qi Qu
||
* Porting PJSIP and G.729 codec (bcg729 implementation) to ESP32.
||
*
||
*
|-

2025-06-09

2025-06-09T10:53:55Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
* ML book (20/326)
||
*
||
*
|-

|-
|Ying Shi
||
* thesis
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Training-Free Multi-Step Speaker Extraction[https://z1et6d3xtb.feishu.cn/docx/AzKrdx96joFYohxXd8Ucfqqbnbg]
||
*
||
*
|-

|-
|Junming Yuan
||
* letter-level ASR finetuning exp on {clean/2-mix/3-mix}(done)[https://z1et6d3xtb.feishu.cn/docx/Azkwd9VrVosk26xtoZ8cbBnuntc]
* some AIGE works
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Write a practice manual for the summer school for Tsinghua middle School.
* Summarize the experimental phenomena[https://z1et6d3xtb.feishu.cn/docx/CdHsdmo8goGNAGxBSGhcB59Nnyd].
||
*
||
*
|-

|-
|Wan Lin
||
* revise paper
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* some tests of Huawei project
* the English version of the AI book(1/4)
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* Data Analysis report in RoyalFlush
* Prepare for Phd interview
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
* Some embedded system development and debugging work in support of AIbabel's new products.
||
*
||
*
|-

2025-05-26

2025-05-26T10:52:14Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Two days of teaching, two days of training
* Refine NS paper
* College version of the AI hand book
||
*
||
*
|-

|-
|Lantian Li
||
* BUPT Graduate matters
* Huawei projects (N&F)
* Kicking off the translation of ML book
||
*
||
*
|-

|-
|Ying Shi
||
* Prepare some material about the Huang Danian Challenge final report.
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Complete the final delivery of Huawei TSE
||
*
||
*
|-

|-
|Junming Yuan
||
* Find bug and revise my ASR code.
* Review Middle-school AI practice handbook(4).
||
*
||
*
|-

|-
|Xiaolou Li
||
* Continue to audit data
* Reading some paper about SSL
||
* Finish data audition, and start to organize all 10k h data
* Pre on this Friday
||
*
|-

|-
|Zehua Liu
||
*Data Audit and paper revise
*Reading paper about Qwen2.5-omni and maybe apply VTS to this model
*Data augmentation for AlignVSR
||
*
||
*
|-

|-
|Pengqi Li
||
* Research progress: A large number of experiments and visualizations, but there is still confusion in "How to display the explanation".
* Teaching work: Prepare for the AI course at Tsinghua middle School and assist with the graduation ceremony.
||
* Summarize the work that has been completed and review similar papers.
||
*
|-

|-
|Wan Lin
||
* Paper reading, Friday report
* Doing some test
* Revised paper
||
*
||
*
|-

|-
|Tianhao Wang
||
* leave absence
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* prepare Huawei project meeting with tianhao
* the English version of the AI book
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* reading paper
* check NS code, modify and supplement exp results
||
*
||
*
|-

|-
|Jiaying Wang
||
* train pure asr system use clean wsj0
** loss setting and data: remove zero_infinity parameter, use speech longer than 6s
** training: loss can converge at under 20(reasonable), LER 45%(higher than expectation)
** plan: change cnn settings, explore whether the performance is related to word length
* HongYan competition slides modification

||
*
||
*
|-

|-
|Yu Zhang
||
* Profit analysis about Multi Agent System
* Reflection time range experiment
* Some Data analysis task in RoyalFlush (external)
||
*
||
*
|-

|-
|Wenqiang Du
||
* New KWS model for AIbabel(30 words and speech enroll)
||
*
||
*
|-

|-
|Yang Wei
||
* Finish AIbabel online KWS model encryption.
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* complete the introduction, method and experimental setup, result is in progress
||
*
||
*
|-
|-
|Qi Qu
||
* Text-enroll KWS models routine work: finding ideal thresholds (word list = Mandarin Chinese 200 words, models = [dist-20250310, dist-20250520]).
||
*
||
*
|-

2025-05-19

2025-05-19T10:52:10Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Training for Tsinghua Primary School
* Training for ZhongLv group
* Refine AIGE book for college students

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Some tests of Huawei project(emotion & targetless)
* Revised Huawei report
||
*
||
*
|-

|-
|Junming Yuan
||
* Extended ASR finetuning exp[https://z1et6d3xtb.feishu.cn/docx/Azkwd9VrVosk26xtoZ8cbBnuntc]
* Review Middle-school AI practice handbook(9/20).
||
*
||
*
|-

|-
|Xiaolou Li
||
* Audit video data
* Improve the speed of inference
* Paper reading
||
*
||
*
|-

|-
|Zehua Liu
||
* Audio video data check
* help xiaolou to transfer web code to GA server
* Paper reading
||
*
||
*
|-

|-
|Pengqi Li
||
* Organize a pre-experiment to explore the following questions:
** How to evaluate reliability(some experiment shows reliability)
** How to visualize (but still thinking about how to display the "explanation").
||
*
||
*
|-

|-
|Wan Lin
||
* multi-scale feature exp: no improvement
* reading paper
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* Use some metrics in audio generation task to evaluate the performance of CLAPSep and our model
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* reading paper
* weekly report
||
*
||
*
|-

|-
|Jiaying Wang
||
* ASR training
** clean data ctc loss converge at 200 (higher than expactation)
** LER have abnormal result：predicted labels tend to concentrate on a few letters, debuging
* Modify the PPT for the hongyan campus competition.
||
*
||
*
|-

|-
|Yu Zhang
||
* For news and sentiment analysis, use reflection as "condition" instead of as "reference" [https://z1et6d3xtb.feishu.cn/docx/SZL2d3y3RolnXlxF02fcK03Bnqd?from=from_copylink]
* Increase news sources (the abuse of reflection is often found when there is a lack of useful news on that day)
* Adding more benchmark (implementing rule based benchmark in TradingAgents (MACD RSI ... ))
||
* Detail Analysis of current backtesting result and check the paper plan with Teacher Li

|-
|Wenqiang Du
||
* Business trip to Changzhou
||
*
||
*
|-

|-
|Yang Wei
||
* Finish license check module for AIBabel ASR gRPC service.
||
*
||
*
|-

|-
|Turi
||
* Defense
||
*
||
*
|-
|Yue Gu
||
* fix a bug about a reproduced method and retrain the model
* polish my introduction according to some suggestions
||
*
||
*
|-
|-
|Qi Qu
||
* On-device text-enroll KWS demo.
* Problem analysis: performance drop caused by precision loss in quantization. [https://b30lttjm7l.feishu.cn/docx/Vkjtd1cjboDD3Ex1xMGcq38WnQe?from=from_copylink]
||
*
||
*
|-

2025-05-12

2025-05-12T10:52:18Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Training at Tsinghua Primary School
* Training for Zhong Lv group
* Training for Beijing 4th Middle School
* AI education material for college school

||
*
||
*
|-

|-
|Lantian Li
||
* Tackle the Huawei Spark Award
* Review graduate theses
* Engage in several academic visits
||
*
||
*
|-

|-
|Ying Shi
||
* Huawei Spark Award
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Completed the delivery of Huawei TSE project
||
*
||
*
|-

|-
|Junming Yuan
||
* Revise MT-HuBERT paper v0.2(done)
* Need extend ASR finetuning exp:
** clean finetuning on LS100: LER-->4.17% on test-clean
** mix finetuning is in progress.
||
*
||
*
|-

|-
|Xiaolou Li
||
* Added new function to VTS Web, enabling ACC2Speech model choosing
* Polished the presentation slide
* Audited a part of our data between 1 January to 7 April
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||

* Review my research (including related papers, code, etc.).
* Organize a pre-experiment to explore the following questions:
** How to visualize
** How to evaluate reliability
||
* Outline of the paper and pre-experiment
||
*
|-

|-
|Wan Lin
||
* Writing paper, finish 1st version
* Multi-scaled feature exp: training, haven't observed improvement by far
||
*
||
*
|-

|-
|Tianhao Wang
||
* Huawei huohua award delivery
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Writing neural scoring paper
* Reading paper
||
*
||
*
|-

|-
|Jiaying Wang
||
* Loss Nan fixed, reason is dimension of linear projection after ctc embedding mismatch the dimension of text label
** after fixed, both linear encoder and conv2d encoder converge well, still training

* Network+ preparation
||
*
||
*
|-

|-
|Yu Zhang
||
* Optimizing Reflection Mechanism (mainly on Rational and The Effective Range of the reflection)
* AED Huawei additional dataset test report delivery (validation model can also reduce the number of parameters on the Huawei dataset)
||
*
||
*
|-

|-
|Wenqiang Du
||
* Check jiaoyubu's AI lesson
* Some of the company's work
** Private deployment of KWS service
** Iteratively upgrade the KWS model using the online data
||
*
||
*
|-

|-
|Yang Wei
||
* Add license check for AIbabel online ASR and KWS (in progress)
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* complete the introduction and related work， method is still in progress（50%）
||
*
||
*
|-
|-
|Qi Qu
||
* Fixed several bugs in converting text-enroll KWS models.
* Some experiments and reports on text-enroll KWS models: [https://b30lttjm7l.feishu.cn/docx/IZlbdBbKpoh5BTxGtlecnMjxnih?from=from_copylink], [https://b30lttjm7l.feishu.cn/docx/Vkjtd1cjboDD3Ex1xMGcq38WnQe?from=from_copylink].
* Consolidating `aibabel_utils` library.
||
*
||
*
|-

2025-04-28

2025-04-28T10:48:39Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Some tests of Huawei project
* Writing the report of Huawei project
||
*
||
*
|-

|-
|Junming Yuan
||
* Make Jiaoyubu's AI lesson PPTs with Qiang bro
* Add 3-mixed test results under 2-mix finetuning setting and revise CN version of MT-HuBERT paper
||
*
||
*
|-

|-
|Xiaolou Li
||
* Write GA doc (test report and mid term report)
* Prepare the presentation PPT
* Improve the VTS demo system
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Make Jiaoyubu's AI lesson PPTs with Qiang bro
* Review my research.
||
*
||
*
|-

|-
|Wan Lin
||
* Finish model training, only some test tasks left
* Write paper: finish intro, related, method
||
*
||
*
|-

|-
|Tianhao Wang
||
* Huawei huohua model training
* demo
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* compared CED topk labels with ground truth labels, most CED labels are parent labels of ground truth(eg.ground truth: Male speech,man speaking; CED label: Speech)
* adjust the order of separating audio from low to high probability, it means that our method is effective(SDR: our method: 12.2182; reversed: 11.8793)
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Continue to write NS paper (finished ver.1, soon discuss with LW)
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* add reflection and memory mechanism based on market feedback (still fine-tuning prompt)
* try other policy fusion method, no significant improvement.
||
*
|-

|-
|Wenqiang Du
||
* Jiaoyubu's AI lesson（10/10）with Junming and Pengqi
* Some tasks about company
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2025-04-21

2025-04-21T10:31:53Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Refine the framework of AI text book of primary school.
* Two talks for Tencent.

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Weekly report
* Huawei project (add cosine loss, get slightly better results)[https://z1et6d3xtb.feishu.cn/wiki/OXubwl2fIip91vkYsgMc1duhnLd]
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*Gongan Document Writing
*Gongan PPT making
*Making presentation system
||
*
||
*
|-

|-
|Zehua Liu
||
*Gongan Document Writing
*Gongan PPT making
*Making presentation system
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* Supply experiments, almost finish, nothing strange
* Start writing paper this week
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Jiaoyubu's AI lesson（7/10）with Junming and Pengqi
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* write the draft of introduction, complement some exps, draw method figure
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2025-04-14

2025-04-14T11:05:35Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AIGE opening ceremoney

||
*
||
*
|-

|-
|Lantian Li
||
* Complete IS rebuttal
* Translate ML book
* Release AIGE web v.10
||
*
||
*
|-

|-
|Ying Shi
||
* 4.11 meeting stuff
* Structure of thesis
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Some model tuning in Huawei projects (training)
* Revise rebuttal
||
*
||
*
|-

|-
|Junming Yuan
||
* make primary school PPT
* some AI practice handbook works
||
*
||
*
|-

|-
|Xiaolou Li
||
* Write document for GA project
* LipVoicer reproduction[https://z1et6d3xtb.feishu.cn/docx/AQWMdHYA2ov4pTxmoAncLW7bn1c?from=from_copylink]
||
*
||
*
|-

|-
|Zehua Liu
||
*Reproduce ACClip2Speech on CNVSRC.Single[https://z1et6d3xtb.feishu.cn/docx/Dg0VdOa2MofEsMxbr2Xcn8MXnUh?from=from_copylink]
*Finish Vocoder code (still on training)
*GongAn document writing
||
*
||
*
|-

|-
|Pengqi Li
||
* developed primary school PPTs (2)
* Co-developed AI practice handbooks with the practice schools (3)
||
*
||
*
|-

|-
|Wan Lin
||
* Some Experiments [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
* huawei project & huohua testing
* personal stuff
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* Sound separation
** baseline: adjust the code of one USS model and evaluate its performance using our test datasets
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Continue all NS exp with 1 layer
* Read paper
||
*
||
*
|-

|-
|Jiaying Wang
||
* explore Whisper: ASR function cannot transcribe mix speech well, the SOT of whisper is on the task level (translate, transcribe, ...)
* modified the model
** using the CTC loss with the minimum loss per iteration backpropagation strategy: loss still turns out to be NaN (problem not in loss caculation)
** replace asr modules to find reason
* other ASR tools
** trying mix speech ASR of FunASR, and attempting to integrate it into the current model

||
*
||
*
|-

|-
|Yu Zhang
||
* Add additional inference step for technical factor analysis (worth for a longer backtesting)
* Done single stock trade pipeline (debug is done, can run backtesting tomorrow)
* Weight avg trading (still debugging)
||
*
||
*
|-

|-
|Wenqiang Du
||
* Prepared for the 4.11 meeting
||
*
||
*
|-

|-
|Yang Wei
||
* Some modification based on the kws patent document from Wenqiang.
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* read the FIP paper carefully， write two introduction paragraphs
* reproduce some hotword exps in new cloud service
||
*
||
*
|-
|-
|Qi Qu
||
* Finished organizing codebase for evaluating KWS models (both "audio-enroll" and text-enroll).
* Text-enroll KWS models evaluation on Mandarin Chinese w/ southern China accent data [https://b30lttjm7l.feishu.cn/docx/NehJdldhOohQX7xjpascFd9vnac?from=from_copylink].
||
*
||
*
|-

2025-04-07

2025-04-07T10:59:33Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
* Submit AI Handbook (College Edition) (10/10)
||
*
||
*
|-

|-
|Ying Shi
||
* Huawei project cooperation
* thesis
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Some tests on the second iteration model of Huawei TSE project
* Revised rebuttal
||
*
||
*
|-

|-
|Junming Yuan
||
* some works with brother Qiang:
** Review primary school PPT
** Make some PPTs
* some AI practice handbook works
||
*
||
*
|-

|-
|Xiaolou Li
||
* Reproduction of ASR component in LipVoicer. Finetuning a new pre-trained Mandarin ASR system is challenging due to the complexity of integrating diffusion steps (or diffusion steps embedding) into a new ASR architecture. Therefore, finetuning the existing checkpoint that was pretrained on English will be a more practical approach.
||
* Finish reproduction in Wed.
* Start to audit new 3000 hours data.
||
*
|-

|-
|Zehua Liu
||
*Finish Lip2Speech model Training(Need Vocoder to reconstruct)
*IS25 Rebutall
||
*
||
*
|-

|-
|Pengqi Li
||
* Some(3) PPTs development
||
*
||
*
|-

|-
|Wan Lin
||
* Experiments[https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]:
** Performance on diff. encoder corresponds to the same encoder
** NS 1layer performs similar to 8layer
||
*
||
*
|-

|-
|Tianhao Wang
||
* Huawei project things
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* did some testing work of sound separation
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Do some mid-term course homework things
* read paper
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
Multi Agent Investment:
long term investment seems useful (better than pervious short term only investment), but still not good than buy and hold baseline
* Policy Level Problem:
** feedback is portfolio level (about to choose which portfolio), need to design stock level feedback.
** The current investment strategy group's strategy generation process is too simplistic and needs to incorporate additional reasoning pipelines.
* Group Level Prombel:
** weight average of different policy instead of choose one from them.
||
*
||
*
|-

|-
|Wenqiang Du
||
* Check AI primary handbook's PPT
* Jiaoyubu's AI lesson（4/10）with Junming and Pengqi
* Some project cooperation about AIbabel
||
*
||
*
|-

|-
|Yang Wei
||
* Test text enroll kws model with southern accent data [https://b30lttjm7l.feishu.cn/docx/N74UdZHhCoa6cPx4C5wccY4Hn9d?from=from_copylink]
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* move my code, model and training envs to new cloud service, reproduce some exps
* read several papers and write the question analysis paragraph
||
*
||
*
|-
|-
|Qi Qu
||
* Reorganizing codebase for evaluating KWS models (audio-enroll and text-enroll).
||
*
||
*
|-

2025-03-31

2025-03-31T10:50:37Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI handbook college version

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Huawei project cooperation
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Training second iteration TSE model for Huawei project ( eol 0db SI-SDR （once:6.963）-> (twice:8.428))[https://z1et6d3xtb.feishu.cn/wiki/OXubwl2fIip91vkYsgMc1duhnLd]
* Check the breakdown of the host to China Unicom
||
*
||
*
|-

|-
|Junming Yuan
||
* MT-HuBERT paper-CN-v0.1(Done)
* some AI handbook works(checking & revisions) with Brother Qiang
* some AI practice handbook works
* Review primary school PPT
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*Paper Reading on last Friday
*Reproducing Accurately Lip2Speech paper，maybe get some Result this week.
||
*
||
*
|-

|-
|Pengqi Li
||
* Urgent tasks with Qiang Brother
** Handbook checking and revisions, PPT development
* Modified the paper for "Design course"
* Courses and report(Tuesday, Saturday, Today)
||
*
||
*
|-

|-
|Wan Lin
||
* Ablation experiments [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
* Experiments for diff. Transformer layers
||
*
||
*
|-

|-
|Tianhao Wang
||
* Huawei project things
** test report
** vggsound 44 classes model training
* Huawei interview
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* Sound separation
** familiar with the code of our model
* check and revise the AI handbooks
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* finished diarization test in vox-e (result is normal)
* read paper
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Summit middl handbook
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* almost finish 5 speakers'exps，plan to write the paper
* plan to give the presentation after accomplishing the introduction
* proofread the AI handbooks
||
*
||
*
|-
|-
|Qi Qu
||
* NPU (MR536) models benchmark regarding speed [https://b30lttjm7l.feishu.cn/docx/IygUdJ16kofcg2xEPnEc7lNsnqb?from=from_copylink].
* KWS models for Chaoshan dialect released.
||
*
||
*
|-

2025-03-24

2025-03-24T10:36:06Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* revisit cohort conditional chain overlap asr and conduct experiments (model is in training)
* thesis
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* Rewrite MT-HuBERT paper (1/5)
* AI practice handbook design of primary school and middle school(contents finished)
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* run ablation experiments [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
* dragon05 data transfer
* 4-mix & 5-mix training
* huawei project things
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* improve code efficiency, continue to test diarization on vox-e
* read paper
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* FIP-based personality-gated adaptation with synthetic data for personal ASR, almost finish preview evaluation exps.
* read 2 TTS-augment papers and reivew an interspeech2025 paper
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2025-03-17

2025-03-17T10:39:42Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI handbook refinment for the college version.

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* thesis
* some school-related stuff
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Complete the training and experimentation of the TSE-IRA model[https://z1et6d3xtb.feishu.cn/wiki/OXubwl2fIip91vkYsgMc1duhnLd] for Huawei, and will write the report
||
*
||
*
|-

|-
|Junming Yuan
||
* prepare report
* double-check middle-school AI handbook(1/7)
||
* write paper
* double-check middle-school AI handbook
* AI practice handbook design of primary school and middle school
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Prepare the AI course for Tsinghua University middle School.
* Add references to the middle handbook(Done)
* Check middle handbook(1/3)
||
*
||
*
|-

|-
|Wan Lin
||
* train ns(multi-enroll) for voxblink1+voxceleb2: perform better than before, but still worse than vc2-only
* retrain multi-scenario ns(multi-enroll) model: consistently better than before now [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
* run ablation experiments: w/o multi-enroll/multi-head/two encoder
||
*
||
*
|-

|-
|Tianhao Wang
||
* sound sep subset training & testing
* huawei interview
* professor Guo's project investigation
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* Sound separation
** train AudioSep on subset data and evaluate it with our testing dataset
** read a paper about USS, try to test this model using our test set firstly(adjusting code in progress)
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Finished diarization test in vox-o
** continue in vox-e
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Check Primary handbook V3.1
* Check middle handbook
* We have Dragon05 (A6000 * 6)
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
* Prepared ppt and poster for ICASSP2025
* Presentation video
||
*
||
*
|-
|Yue Gu
||
* synthesize 100h for each target spk and use KL loss as the regular term, the CER of target speakers reduce 10%.
||
*
||
*
|-
|-
|Qi Qu
||
* Android demo of Text-enroll KWS model.
||
*
||
*
|-

2025-03-17

2025-03-17T10:39:11Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI handbook refinment for the college version.

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* thesis
* some school-related stuff
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Complete the training and experimentation of the TSE-IRA model[https://z1et6d3xtb.feishu.cn/wiki/OXubwl2fIip91vkYsgMc1duhnLd] for Huawei, and will write the report
||
*
||
*
|-

|-
|Junming Yuan
||
* prepare report
* double-check middle-school AI handbook(1/7)
||
* write paper
* double-check middle-school AI handbook
* AI practice handbook design of primary school and middle school
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Prepare the AI course for Tsinghua University middle School.
* Add references to the middle handbook(Done)
* Check middle handbook(1/3)
||
*
||
*
|-

|-
|Wan Lin
||
* train ns(multi-enroll) for voxblink1+voxceleb2: perform better than before, but still worse than vc2-only
* retrain multi-scenario ns(multi-enroll) model: consistently better than before now
* run ablation experiments: w/o multi-enroll/multi-head/two encoder
||
*
||
*
|-

|-
|Tianhao Wang
||
* sound sep subset training & testing
* huawei interview
* professor Guo's project investigation
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* Sound separation
** train AudioSep on subset data and evaluate it with our testing dataset
** read a paper about USS, try to test this model using our test set firstly(adjusting code in progress)
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* Finished diarization test in vox-o
** continue in vox-e
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Check Primary handbook V3.1
* Check middle handbook
* We have Dragon05 (A6000 * 6)
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
* Prepared ppt and poster for ICASSP2025
* Presentation video
||
*
||
*
|-
|Yue Gu
||
* synthesize 100h for each target spk and use KL loss as the regular term, the CER of target speakers reduce 10%.
||
*
||
*
|-
|-
|Qi Qu
||
* Android demo of Text-enroll KWS model.
||
*
||
*
|-

2025-03-10

2025-03-10T10:47:42Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||

* Revise AI textbook of the colleage version

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Compare Ascend and Nvidia
** Performance: Clean ASR task 20epochs WER 6.91% : 7.02% (Ascend vs Nvidia)
** Speed: Nvidia is one time faster than Ascend
* Start think about my thesis
||
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* Pretraining work:
** MT-HuBERT & Cocktail-HuBERT will be finished next week.
** Get a set of comparable finetuning results(15/5/3-shot) for each pretrain model at the 400K training step.[https://z1et6d3xtb.feishu.cn/docx/ElAKdh07GoD8qKxGFLfc3seAnOh]
* Check and add reference for AI junior high school handbook(1/2).(Done)
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*Writing NFSC document
*Lora finetune VLM(both Encoder and LLM Decoder) result seem not very well(maybe need parameeter adjustment)
*Pretrained VSR Encoder + VLM(Decoder) seems better than Normal LM
||
*Design VTS architecture and implement it
||
*
|-

|-
|Pengqi Li
||
* Prepare the AI course for Tsinghua University Junior High School.
* Add references to the handbook(junior high school version 1/2)(Done).
||
*
||
*
|-

|-
|Wan Lin
||
* Supply NS experiments [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
* Help xiaochen reproduce the diarization SV method
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* speaker diarization baseline for NS (mix test: baseline EER 15.972% -> 12.983%) others still testing...
* make ppt about scaling law on speaker volume.
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* Multi Agent Investment
** use Top 31 stocks in 11 sector to do portfolio for better correlation with input news (no excess return)
** analysis the trading decision
* Huawei AED
** smallest model to keep AUC excess 0.9
** split inference into two phase (Phase 1: Human Voice vs None Human Voice, Phase 2: Speech vs Other Human Voice) with two smaller model
||
*
||
*
|-

|-
|Wenqiang Du
||
* Check Primary handbook V3.0（Done）
** Add reference(80%)
||
*
||
*
|-

|-
|Yang Wei
||
* Adapt text enroll kws model with synthesized dialect data.(recall: 83% -> 94%)[https://z1et6d3xtb.feishu.cn/docx/WFBJdF3D0o6w6bxHCJBcn9DIndg]
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* a 0.4% CER reduction has achieved for one spk, but no improvement was discovered on other spks. I'm still do some exps.
* restart the synthetic-data related exps, try to fill the gap between synthetic data and real data on the output distribution of model.
||
*
||
*
|-
|-
|Qi Qu
||
* Technical investigation on Visual Event Detection.
* Experiment on annotating and auditing audio with Audio LLM: insufficient VRAM; poor I/O in CPU/GPU hybrid mode.
||
*
||
*
|-

2025-03-03

2025-03-03T10:57:00Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Three slides for AIGE to gov and enterprise.

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Prepare Ascend Sever environment
* training Conditional Chain overlap ASR model with Hierachical-Transformer [https://z1et6d3xtb.feishu.cn/docx/UPxGdBl4Zo6JapxHmsXcI14Pngg?from=from_copylink here]
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Training TSE model for free content enrollment（for Huawei & CSSC(中船) projects）
* Reading papers about refiner
||
*
||
*
|-

|-
|Junming Yuan
||
* Finish MPC-HuBERT pretrain.
* Double check the related experimental code.
** MT-HuBERT(in progress) & Cocktail-HuBERT need re-pretrain.
** The results of other baseline in [https://z1et6d3xtb.feishu.cn/docx/VThUd30RPoTBR4xOiKYc4gQTnsb here]
||
*
||
*
|-

|-
|Xiaolou Li
||
* VSR training (1500h) cnvsrc-single valid 300 CER: 36.14% (not converged)
* Finish pre-processing 4000h data
* get ASR transcript for 4000h data
* Writing NSFC document
||
*
||
*
|-

|-
|Zehua Liu
||
*Paper Reading and Sharing in last Friday
*Writing Vision Language Model code
*Writing NSFC document
||
*
||
*
|-

|-
|Pengqi Li
||
* Prepare the AI course for Tsinghua University Junior High School.
* Using t-SNE to visualize the factorized content vector.
** Next step is to color(speaker information importance or not) each point.
||
*
||
*
|-

|-
|Wan Lin
||
* try some adjustment for clean performance（no improvement）
* supply experiments for other tests
||
*
||
*
|-

|-
|Tianhao Wang
||
* sound separation: 2-mix and 3-mix model training
* weekly report
||
* subset data training
||
*
|-

|-
|Xiaoxue Luo
||
* generation of multi-mix audio data and did some test experiments.
* read papers
||
*
||
*
|-

|-
|Zhenyu Zhou
||
* finish graduation thesis
||
*
||
*
|-

|-
|Junhui Chen
||
* Reproducing speaker diarization method for NS (debugging...)
* read paper
||
*
||
*
|-

|-
|Jiaying Wang
||
* debug ctc loss part[https://z1et6d3xtb.feishu.cn/docx/TUHldiaoQoYBqux7JEhcaCXenzh]
||
*
||
*
|-

|-
|Yu Zhang
||
* AED:
** Split AED model into two smaller model to detect the human voice in noisy environments and in clean environments separately.
** Trying smaller model (under 200K)
* Multi Agent Investment
** try index enhancement trading, no obvious excess return
||
* try do portfolio investment on some selected big company
* add the debate topic about the logical consistency inside investment decisions.
||
*
|-

|-
|Wenqiang Du
||
* Primary handbook's PPT (24/44)
* Continue to check Primary and middle handbook(Completed this week)
* Speech cloning sample for the company

||
*
||
*
|-

|-
|Yang Wei
||
* Tuning text enroll kws model for dialect data with linear layer. (recall: 65%->85%->94%)
||
*
||
*
|-

|-
|Turi
||
* Thesis writing
* Result with LM[https://z1et6d3xtb.feishu.cn/docx/JvDsd8zR4oMwnyxQEQdckpMjn7m?from=from_copylink]
||
*
||
*
|-
|Yue Gu
||
* finish some exps, but nothing is improved.
* finish a proposal，I will present it recently
||
*
||
*
|-
|-
|Qi Qu
||
* Applying pre-prod eval routine on text-enroll KWS models: the ideal thresholds for each keyword vary significantly.
||
*
||
*
|-

2025-03-03

2025-03-03T10:17:02Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* Finish MPC-HuBERT pretrain.
* Double check the related experimental code.
** MT-HuBERT(in progress) & Cocktail-HuBERT need re-pretrain.
** The results of other baseline on [https://z1et6d3xtb.feishu.cn/docx/VThUd30RPoTBR4xOiKYc4gQTnsb here]
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* try some methods for clean performance（no improvement）
* supply experiments for other tests
||
*
||
*
|-

|-
|Tianhao Wang
||
* sound separation: 2-mix and 3-mix model training
* weekly report
||
* subset data training
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Primary handbook's PPT (24/44)
* Continue to check Primary and middle handbook(Completed this week)
* Speech cloning sample for the company

||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* finish some exps, but nothing is improved.
* finish a proposal，discussing…?
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2025-02-17

2025-02-17T10:54:50Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Middle-School education PPT

||
*
||
*
|-

|-
|Lantian Li
||
* Final version proofreading of the high-school book (17/40)
* Polish IS2025 papers.
||
*
||
*
|-

|-
|Ying Shi
||
* Conditional chain overlap asr
** pooling order
** padding chain
** augmentation padding
** [https://z1et6d3xtb.feishu.cn/docx/Wg3ldbCKeoKhBzxZ2lccTO8ZnTf?from=from_copylink here]
||
*
*
||
*
|-

|-
|Zhenghai You
||
* Completed the revision of the second edition of the paper
||
*
||
*
|-

|-
|Junming Yuan
||
* The results of MT-Hubert/Cocktail-Hubert/Hubert on LS960[https://z1et6d3xtb.feishu.cn/docx/DRICd10VCodDfOxXbDMcI97snod]
**15-shot finetuning(clean/Mixup/MT):MT-HuBERT > Cocktail-Hubert > Hubert
** MPC-Hubert is still in the training queue
||
*
||
*
|-

|-
|Xiaolou Li
||
* Paper modification
* Data processing (2000h / 4000h)
* Some new demand in data collection server
* Paper reading
||
*
||
*
|-

|-
|Zehua Liu
||
*CNVSRC 2024 and VSR-LLM paper writing and revise, and do some relevant Experiments.
||
*
||
*
|-

|-
|Pengqi Li
||
* XAI of Speaker Verification[https://z1et6d3xtb.feishu.cn/docx/QnZvdrNAboVCCVxgVRzcpsgRn6d]
** some experiment looks like successful
** Writing paper same time(30%)
*Report recently work on Friday
||
*
||
*
|-

|-
|Wan Lin
||
* alter training strategy to 2-positive multi-enroll for mix-training
* find and fix some tiny bugs
* results [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* Check the pictures in AI high school handbook,will be completed in these days
* The learning and production of AI daily signature
||
*
||
*
|-

|-
|Zhenyu Zhou
||
* Graduation article
* interspeech paper with zhenghai
* code double check with jiaying
||
*
||
*
|-

|-
|Junhui Chen
||
* Read paper about e2e SV / loss (little useful content for NS).
* Continue to think and try other tricks, but no meaningful results yet.
||
*
||
*
|-

|-
|Jiaying Wang
||
* conditional chain with ctc experiment
** loss decreased slowly in the previous few epochs, almost stop at around -3
** checked the model code: no bug
** test results of these epoch to determine the problem
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*Continue to check AI primary handbook（done）
*Continue to check AI middle handbook（done）
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
* Thesis writing
* Trained the language model, some bugs when decoding with LM
||
*
||
*
|-
|Yue Gu
||
* fine-grained personality-gating method：finish the code and model training，ready to test
||
*
||
*
|-
|-
|Qi Qu
||
* Successful porting of text-enroll KWS models (hybrid quantization) to mr536 w/ low precision loss, same RT as previous version (which shows drastic precision loss). [https://b30lttjm7l.feishu.cn/docx/WORcdiE1io86Agxg9hOcKIO0nwe?from=from_copylink]
||
*
||
*
|-

2025-02-10

2025-02-10T10:26:18Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* Revised NS paper for IS2025 [https://z1et6d3xtb.feishu.cn/docx/PqtDdWPSwomSDexW2oUc2M4qnrc?from=from_copylink] (still lack of experimental results)
* Train multi-scenario model (need parameters adjusting, still in training)
* Try other revised-BCE loss(failed)
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* faster test code for NS (Vox-O 25min -> 5min)
* writing paper for is25
* (On plane to Beijing)
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* refine prompt
* add backtesting report to debate report
* trying stronger model (DeepSeek R1 70B)
||
* introduce more trading groups that are mutually opposed.
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2025-01-13

2025-01-13T10:33:09Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI handbook high-school version, recheck
* Publication stuff

||
*
||
*
|-

|-
|Lantian Li
||
* Go on AI-Graph EN (49/50)
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* Check the high school AI handbook(done)
* Organize our photos
* The results of MT-Hubert on LS960[https://z1et6d3xtb.feishu.cn/docx/HUIad3uqgozpEyxIwuTcU9uInsb]
**2-mixed Test: 400K steps top-2 ACC: 74.63% ---> 1600K steps top-2 ACC: 79.43%
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* IS25 Proposal almost done
** writing the experimental part
** checks and analysis the result
* Go to the hospital for a follow-up and return lab.
||
*
||
*
|-

|-
|Wan Lin
||
* NS: Adopt multi-enroll, margin-bce and long-duration test to resnet+transformer model: EER 1.23%->1.13%
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
* IS2025 proposal[https://z1et6d3xtb.feishu.cn/docx/T8IvdtN32o8kHWxqcPvc5LsWnce]
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Check Primary handbook
** Related PPT and Jiaoan
*Some project cooperation
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* design the fine-grained personality extractor to produce the phone-level voice charactor similarity (code is in progress)
* check the primary school handbook
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2024-01-06

2025-01-06T10:39:13Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* NS: multi-enroll+margin bce: 1.638% -> 1.521% (5w spk)
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2024-01-06

2025-01-06T10:38:57Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* NS:multi-enroll+margin bce: 1.638% -> 1.521% (5w spk)
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2024-12-30

2024-12-30T10:39:47Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Zhenghai You
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
* MT-Hubert paper writing(1/2)
* Check the high school AI handbook(237/362)
||
*
||
*
|-

|-
|Xiaolou Li
||
* Data process server code upgrade, data transfer
* Experiment on 1500h (in training...)
* Odds and ends...Paper reading, Coursework, Calendar delivery...
||
* Upgrade the AV-HuBERT training code and test it
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Conduct a preliminary experiment for the proposal(IS25-XAI) (A clear doc must be produced by the end of this week.)
* Check the high school AI handbook(1/3)
||
*
||
*
|-

|-
|Wan Lin
||
* NS: margin BCE loss & multi-enroll training
||
*
||
*
|-

|-
|Tianhao Wang
||
*
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Nothing~
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Turi
||
*
||
*
||
*
|-
|Yue Gu
||
* read several papers about synthetic data for personalized ASR and do some exps. plan to report them on this friday or next monday.
||
*
||
*
|-
|-
|Qi Qu
||
*
||
*
||
*
|-

2024-12-23

2024-12-23T10:59:07Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI handbook high-school version done (v1.1).
* 3rd training for Tsinghua middle school
||
*
||
*
|-

|-
|Lantian Li
||
* Optimize 2025 calendar (6th round) and finalize for mass printing.
* Complete the 2nd round of master viva defence.
* Complete two Huawei project delivery.
* Finish my annual performance review.
||
*
||
*
|-

|-
|Ying Shi
||
* Conditional-chain overlap asr
** Condition augmentation & condition detection (is running now)
** remove Decoder and investigate whether speech encoder can find the order only depend on CTC Loss and self-attention
* More tests for next diting (hope can be started within this week)
** google phone test
** Separation model test (thx tianhao, zhenyu)
* Final round interview
||
*
||
*
|-

|-
|Zhenghai You
||
* Huawei TSE Delivery Package
||
*
||
*
|-

|-
|Junming Yuan
||
* MT-Hubert paper writing(1/4)
* Check the primary/middle school AI handbook
||
* Go on MT-Hubert paper writing
* Check the high-school AI handbook
||
*
|-

|-
|Chen Chen
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Check the primary/middle school AI handbook
* Conduct a preliminary experiment for the proposal(IS25-XAI)(But not ideal).
||
* Continue thinking about how to conduct the proposal.
||
*
|-

|-
|Wan Lin
||
* NS
** Add infoNCE loss: failed
** Expand model parameters: in training, sever died
||
*
||
*
|-

|-
|Tianhao Wang
||
* weekly reading
* Huawei project things
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* write some course papers
||
* prepare for the final exam
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
* 4 course homework/paper
* review for 3 math exams
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* Huawei AED Delivery Package
* Royal Flush server base development environment setup
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
* Text enroll KWS
** Small data experiment for no cross attention model and filtered wenetspeech [https://z1et6d3xtb.feishu.cn/docx/WhzYdPwUJosDmhx5HPAcZG94nBe]
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Thesis writing
* Personal stuff (Setting up a website for African students Association in THU..)
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
* KWS: finding ideal thresholds for zh10 model (2024-12-13) optimized for exhibition scene.
* Quantization of Text-Enroll models: huge precision loss.
* NPU metrics: [https://b30lttjm7l.feishu.cn/docx/WORcdiE1io86Agxg9hOcKIO0nwe?from=from_copylink report] (to be updated)
||
*
||
*
|-

2024-12-16

2024-12-16T10:56:06Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* High-school AI handbook recheck
* Talk on Hebei Education conference
* Paper review for TASLP

||
*
||
*
|-

|-
|Lantian Li
||
* Prepare 2025 Calendar (4th round, thx Xue/Lou)
* Review BUPT Master Viva Report (Done)
* Apply BUPT Innovation Scholar (Failed... Fxxk)
* Submit NSFC Annual Report (Done)
* Prepare some materials for another rubbish project...
||
* Go on AI-Graph EN Chapter 4 (37/50)
* Two HUAWEI projects delivery
||
*
|-

|-
|Ying Shi
||
* Revise the HUAWEI Project Proposal
** more test about Google App and write test report
* Prepare for the Interview
||
* Back to conditional chain-overlap asr model
||
*
|-

|-
|Zhenghai You
||
* Huawei Stage II Model Training and Experimental Testing
* Revise Topicreport
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*Start-term Document Revise
*Some Corruption Exp(still training)
*Upload GA data to server
||
*
||
*
|-

|-
|Pengqi Li
||
* paper reading
* Check the primary school version(8/10)
||
* Make Proposal for IS25 Special Session of XAI
||
*
|-

|-
|Wan Lin
||
* NS
** Solve the problem of slow training
** Results [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
* Revise Start-term Document
* paper reading
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* polish the 2025 calendar
* prepare a course presentation
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*Submit interim report
*Some personal matters
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* Huawei AED Delivery Package
* Revise Topicreport
||
*
||
*
|-

|-
|Wenqiang Du
||
* update Exhibition scene KWS model [https://z1et6d3xtb.feishu.cn/docx/J3gVdqPc9o31WrxCGSpcvjo8nOr?from=from_copylink]
* Tencent AI Course Development（2/35）
** 2 Sample Courses（80%）
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Evaluated ASR model using CER (6.08%) & Thesis writing
* Application for University
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
* NPU confirmed working for both Zeus-KWS and CED models on both mr536 and v851se platforms: dynamic fixed point int16 quantization.
* KWS training data processed for Yichang (Hubei) dialect: 6 keywords.
||
* Adapt Text-Enroll-KWS model(s) to mr536 NPU.
||
*
|-

2024-12-09

2024-12-09T10:56:17Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* High-school AI handbook (1/4)
* Examination sheet for AI challenge in Hebei

||
*
||
*
|-

|-
|Lantian Li
||
* Check high school AI book (Done)
* Polish 2025 Calendar (2nd round)
* BUPT master Viva talk
||
* AI-Graph EN Chapter 4 (37/50)
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Zhenghai You
||
* Developing viva presentation
||
*
||
*
|-

|-
|Junming Yuan
||
* Add a Mixture Predictive Coding(MPC)-hubert experiment[https://z1et6d3xtb.feishu.cn/docx/Elild36IDoiGpfxYsYUcfoJwnWf].
** 2-mixed test: clean-Hubert < MPC-Hubert < cocktail-Hubert < MT-Hubert
||
* writing paper
||
*
|-

|-
|Chen Chen
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
* Preparing for proposal pre and report
||
*
||
*
|-

|-
|Zehua Liu
||
*Start term report and start-term material writing
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* Friday report
* NS 5W spk model: still training, haven't observed improvement
||
*
||
*
|-

|-
|Tianhao Wang
||
* start-term stuff
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* production of 2025 Calendar(v0.1 done)
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*Mid term report and mid-term material writing
||
*
||
*
|-

|-
|Junhui Chen
||
* got a bad fever
* prepare for final exam
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* prepare thesis start term report
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Started writing thesis
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
* Finding ideal thresholds for model `zh48+chongqing15:v2-20241202`, which outperforms the previous one.
* SDK set up for `v851se`. Quantized KWS model works, ~17ms per inference. Some tiny bugs need further investigation.
||
*
||
*
|-

2024-12-09

2024-12-09T10:55:36Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* High-school AI handbook (1/4)
* Examination sheet for AI challenge in Hebei

||
*
||
*
|-

|-
|Lantian Li
||
* Check high school AI book (Done)
* Polish 2025 Calendar (2nd round)
* BUPT master Viva talk
||
* AI-Graph EN Chapter 4 (37/50)
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Zhenghai You
||
* Developing viva presentation
||
*
||
*
|-

|-
|Junming Yuan
||
* Add a Mixture Predictive Coding(MPC)-hubert experiment[https://z1et6d3xtb.feishu.cn/docx/Elild36IDoiGpfxYsYUcfoJwnWf].
** 2-mixed test: clean-Hubert < MPC-Hubert < cocktail-Hubert < MT-Hubert
||
* writing paper
||
*
|-

|-
|Chen Chen
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
* Preparing for proposal pre and report
||
*
||
*
|-

|-
|Zehua Liu
||
*Start term report and start-term material writing
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* Friday report
* NS 5W spk model: haven't observed improvement
||
*
||
*
|-

|-
|Tianhao Wang
||
* start-term stuff
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* production of 2025 Calendar(v0.1 done)
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*Mid term report and mid-term material writing
||
*
||
*
|-

|-
|Junhui Chen
||
* got a bad fever
* prepare for final exam
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* prepare thesis start term report
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Started writing thesis
||
*
||
*
|-
|Yue Gu
||
*
||
*
||
*
|-
|-
|Qi Qu
||
* Finding ideal thresholds for model `zh48+chongqing15:v2-20241202`, which outperforms the previous one.
* SDK set up for `v851se`. Quantized KWS model works, ~17ms per inference. Some tiny bugs need further investigation.
||
*
||
*
|-

2024-12-02

2024-12-02T10:54:25Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Some personal stuff
* Find some numerical issues of current conditional model (will be fixed in this week)
||
*
||
*
|-

|-
|Zhenghai You
||
* Huawei TSE IRA Demo[https://z1et6d3xtb.feishu.cn/docx/OyOKdtjGJoQBDxxEalScvEKynLg]
||
*
||
*
|-

|-
|Junming Yuan
||
* Some varient experiments with MT-HuBERT[https://z1et6d3xtb.feishu.cn/docx/NErQdl2Hkoa6hSx8qFrc4LQInzc]
* get familiar with text-enroll experiment
||
*
||
*
|-

|-
|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* NS: all transformer
** 5w spk + multi-enroll: EER 1.67%
** variable-length training & adding spk
||
*
||
*
|-

|-
|Tianhao Wang
||
* Some test for out-of-domain text query gap [https://z1et6d3xtb.feishu.cn/docx/KprndYrp3oe8KJxedj8cD8Yfnvd]
* thesis proposal
||
* thesis proposal
||
*
|-

|-
|Xiaoxue Luo
||
* production of 2025 Daily Sign(5/12)
||
* production of 2025 Daily Sign(12/12)
||
*
|-

|-
|Zhenyu Zhou
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* thesis proposal
* paper reading about Multi-Agent Collaboration
** Cooperation in Different Roles
** Competition in the Same Role
||
*
||
*
|-

|-
|Wenqiang Du
||
* Project cooperation communication
** Tencent
** dongxin- technical report about vpr
** zhongchuan - local asr
** Heeryuan - In bidding about RAG

||
*
||
*
|-

|-
|Yang Wei
||
* Train text enroll kws model with 7000h data with spec aug[https://z1et6d3xtb.feishu.cn/docx/WLLLd2zQvoiE78xfMhpcHejdnnd]
* Experiment about inference rtf.[https://z1et6d3xtb.feishu.cn/docx/Sgo3dCvmqoovXOxvneYcBnXOnoh]
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Paper reading
||
*
||
*
|-
|Yue Gu
||
* ablation study about adaptation data, badcase analysis [https://z1et6d3xtb.feishu.cn/wiki/VPZfwx53ei2zkgkSvPtcCiDSnVh?from=from_copylink]
* read several papers about synthetic data for data argumentation
||
*
||
*
|-
|-
|Qi Qu
||
* Finding ideal thresholds for `zh48+henan22` and `zh48+chongqing15` KWS models. `zh48+chongqing15` performs poorly and needs re-arranging word list and retraining.
* NPU development/test environment setup: mr536 and v851se (new).
||
*
||
*
|-

2024-11-11

2024-11-11T11:00:27Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Tianjian AI book (done)
||
*
||
*
|-

|-
|Lantian Li
||
* Complete all the script for the 2025 AI calendar
* AI-Graph EN (32/50)
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Zhenghai You
||
* Huawei project with IRA-TSE[https://z1et6d3xtb.feishu.cn/docx/R05DdrPVqoSzQYxNlhicedxenkd]
||
*
||
*
|-

|-
|Junming Yuan
||
* re-check some details from Cocktail HuBERT paper and prepared the code.
**pseudo-label preparation finished.
* paper reading
||
*
||
*
|-

|-
|Xiaolou Li
||
* Finish VTS documents with Zehua
* Process the CVS3 data
* Inherit the AV-HuBERT training code and debug
||
*
||
*
|-

|-
|Zehua Liu
||
*Finish 2 VTS documents with Xiaolou
**Financial Document
**Technical Document
*Paper Reading on last Friday
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Wan Lin
||
* NS: detection
** clean: 1.479% EER vs. 1.239% EER
** multi: in training
||
*
||
*
|-

|-
|Tianhao Wang
||
* ablation study about some new approach for sound separation [https://z1et6d3xtb.feishu.cn/docx/NLlsdyLtuoptjYxjcX0cwlVbnXc]
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* paper reading to investigate some new approach for sound separation
* retrain AudioSep with a DPRNN block(AudioSep-DP)
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*Attemp to add silence loss during training（seems like useless）
*Conditional Chain 2-5 mix results（still some bugs，the acc of speaker number is poor）[https://z1et6d3xtb.feishu.cn/docx/D2UQdxMBvojkF9xCXGfcFBLGned]
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* SocioDojo
** Single stock (TSLA) investment (still running)
* Investigate some Text guided LLM centric time-series forecaster and reproduce some of them (Time-LLM LLM-Process, AutoTimes), and some toy experiment about how prompt prefix influence the forecast result
||
*
||
*
|-

|-
|Wenqiang Du
||
* Training of New language Models(Cantonese)
* Prepare the PPT for the competition
||
*
||
*
|-

|-
|Yang Wei
||
* Train text enroll KWS model with 7000h data
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* kws data preparation and checking some implementations
* Paper Reading about kws
||
*
||
*
|-
|Yue Gu
||
* use CosyVoice model to synthesize the target speaker utterance, which is employed as the supplement for target speaker adaptation. The adaptation exp is running.
* icassp 2025 paper review
* paper writing
||
*
||
*
|-
|-
|Qi Qu
||
* KWS:
** Yi (Liangshan, Sichuan) test dataset annotated and finalized. Optimal thresholds for predefined scenes. Cloud model service deployed.
** Quantization for NPU with more calibration data (6k): mean_loss=1.3e-4, max_loss=6.2e-2.
** NPU demo: feature extraction + model inference.
** Text-enroll method: android demo benchmark.
||
*
||
*
|-

2024-11-04

2024-11-04T10:58:17Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI Medical sector 2 chapters done
||
*
||
*
|-

|-
|Lantian Li
||
* Submit three papers supporting ICCIP 2024.
* Go on designing 2025 AI daily posts
* Attend CSTR 40th anniversary
||
*
||
*
|-

|-
|Ying Shi
||
* Stop strategy for Cohort Overlap ASR [https://z1et6d3xtb.feishu.cn/docx/KKVHd8EDWoTkjexNhG5cbAWunfb?from=from_copylink here]
||
*
||
*
|-

|-
|Zhenghai You
||
* Huawei project (Unsuccessful IRA) [https://z1et6d3xtb.feishu.cn/docx/RnHLdHO0jobr8uxajiQcvZx6nyc]
* Summarize SPK-AUG experiments[https://z1et6d3xtb.feishu.cn/docx/IiNhdn9xroVlomxdKmxc8B3Cnqe]
||
*
||
*
|-

|-
|Junming Yuan
||
* paper reading
* prepare to reproduce cocktail HuBERT (in progress)
||
*
||
*
|-

|-
|Chen Chen
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
* Debug the Chinese VTS (in training already)
* Process the data of CVS3
* Write the report of VTS project (main work)
||
*
||
*
|-

|-
|Zehua Liu
||
*In-Context-Learning（if sentence is very long，context seems fail）still finding reason
** （context<30s）45.30% | 44.69% (context = 30s) | 46.02%(context = 120s)
*Writing VTS project document
||
*
||
*
|-

|-
|Pengqi Li
||
* New Process of consistency of TAO and LayerCAM.[https://z1et6d3xtb.feishu.cn/docx/VtlIdFxdRodp8Nx8oQjcVLC4nCd]
||
*
||
*
|-

|-
|Wan Lin
||
* NS:detection (edit code with Chen)
** EER of the model decrease faster in the previous epochs
||
*
||
*
|-

|-
|Tianhao Wang
||
* investigating some new approach for target sound separation
* prepare the code for LoRA tuned CLAP
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* prepare the report
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*Reproduction：conditional TasNet [https://z1et6d3xtb.feishu.cn/docx/D2UQdxMBvojkF9xCXGfcFBLGned]
||
*
||
*
|-

|-
|Junhui Chen
||
* NS with frame-level detection loss
** use silero-vad
** Model is training, seems EER decrease faster.
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* SocioDojo
** with cash ratio risk aware, and change information sources, seems have a decent risk control over Nasdaq 100 index [https://z1et6d3xtb.feishu.cn/docx/E6JHdDItzoUe1Ix7Bkfcp435n5b?from=from_copylink]
* Some paper reading and report in RoyalFlush, get some idea (mainly about LLM for time series task)
||
*
||
*
|-

|-
|Wenqiang Du
||
*Training of New Dialect Models(Yi language )
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* LoRA finetuning (Result is not good)
* Data cleaning
||
*
||
*
|-
|Yue Gu
||
* read several paper about speech tokenizer. I want to design a encoder, which processes different size feature frame and construct several different codebooks, to extract personality from the varing speech speed. It is still in progress.
* paper writing
||
*
||
*
|-
|-
|Qi Qu
||
* KWS:
** Yi (Liangshan, Sichuan) dataset prepared for training; dataset to be annotated for testing.
** Experiments on model quantization for NPU devices: i16 quantization arrives at a balance between accuracy and efficiency (~2ms per inference, compared to ~250ms for non-quantized); more calibration data needed for further confirmation.
** Full-featured demo (recording + feature extraction + model inference) for NPU devices in development.
||
*
||
*
|-

2024-10-28

2024-10-28T10:54:19Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI primary book done
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* revise the code about cohort-overlap asr [the training is in progress]
** Support arbitrary source mixing training
** Use the real hypothesis by Token error rate
** Design stop criterion
||
*
||
*
|-

|-
|Zhenghai You
||
* Introduce more hard samples to improve model performance[https://z1et6d3xtb.feishu.cn/docx/CURxdy3tEorxkrxtjjqcdMaYnJg]
** SPK-AUG with same length: There is an improvement, but the SI-SDR decreases when hard sample rate increases
** Design more hard samples
||
*
||
*
|-

|-
|Junming Yuan
||
* The result of time-mask MT-HuBERT [https://z1et6d3xtb.feishu.cn/docx/P62VdvJ9ooDxogx1Q09cM8Zmnd2]
** A sad news
||
*
||
*
|-

|-
|Chen Chen
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
* VTS with LLM structure design and baseline code writing [https://z1et6d3xtb.feishu.cn/docx/ZBnOdEMxgo8bs5xrkb1cPZnCnQg?from=from_copylink]
||
*
||
*
|-

|-
|Zehua Liu
||
*Reading Papper about In-Context-Learning in ASR
*Training model with Adaptive Time Mask
*Try In-Context-Learning with only previous sentence[https://z1et6d3xtb.feishu.cn/docx/JBsidACDVojhCaxFQLbcCVbsnAc?from=from_copylink]
*VTS Project Report starts
||
*
||
*
|-

|-
|Pengqi Li
||
*Consistency of TAO and LayerCAM
** Change TAO from input to final conv layer and obtain more consistency.(Aishell:0.93 in any model)
||
*
||
*
|-

|-
|Wan Lin
||
* NS: downsampling is not useful [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
* share speaker meeting in Friday
||
*
||
*
|-

|-
|Tianhao Wang
||
* AudioSep (CLAP) 5-mix exps:
** text-query: SDR=4.978, SI-SDR=1.972
** audio-query: SDR=6.907, SI-SDR=5.058
** This results with the loudness limitation
||
* AudioSep (CLAP) without loudness limitation
* Project things
||
*
|-

|-
|Xiaoxue Luo
||
*Comparative experiment between AudioSep and baseline system(CLIPSep)
*Prepare the report
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*reproduce 5-mix speech Separation results：
**pit：2-mix：16.04 ；5-mix：6.87
**conditional：5-mix：5.38（40 epoch）
||
*
||
*
|-

|-
|Junhui Chen
||
* NS：speaker detection （method survey & debug）
* get sick
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* SocioDojo (still worse than Nasdaq100 baseline)
** Change information sources, from the perspective of the report generated by LLM, more new information sources will be referenced.
** Prompt Actuator to consider current cash ratio before investing (with out this, the asset ratio goes up to 100%, which leads to high risks, still running)
* Read some papers about integrating time series into LLM
||
*
||
*
|-

|-
|Wenqiang Du
||
* Prepare data,code and environment for Pro.Mijiti
||
*
||
*
|-

|-
|Yang Wei
||
* Train text enroll KWS model with Aibabel training data. Not work.
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Whisper-largev3 finetuning
** Freezing 20 layers of encoder achieved 9.75 WER. Vanilla finetuning 8.02 WER
||
*
||
*
|-
|Yue Gu
||
* seek suggestions from other authors. Many suggestions are conflicting, so I'm try to figure out the reasons and fix these issues.
||
*
||
*
|-
|-
|Qi Qu
||
* KWS:
** Text-enroll models exported to ONNX.
** C/JNI libs built based on ONNX models and ready for on-device test.
||
*
||
*
|-

2024-10-28

2024-10-28T10:50:17Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI primary book done
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* revise the code about cohort-overlap asr [the training is in progress]
** Support arbitrary source mixing training
** Use the real hypothesis by Token error rate
||
*
||
*
|-

|-
|Zhenghai You
||
* Introduce more hard samples to improve model performance[https://z1et6d3xtb.feishu.cn/docx/CURxdy3tEorxkrxtjjqcdMaYnJg]
** SPK-AUG with same length: There is an improvement, but the SI-SDR decreases when hard sample rate increases
** Design more hard samples
||
*
||
*
|-

|-
|Junming Yuan
||
* The result of time-mask MT-HuBERT [https://z1et6d3xtb.feishu.cn/docx/P62VdvJ9ooDxogx1Q09cM8Zmnd2]
** A sad news
||
*
||
*
|-

|-
|Chen Chen
||
*
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*Reading Papper about In-Context-Learning in ASR
*Training model with Adaptive Time Mask
*Try In-Context-Learning with only previous sentence[https://z1et6d3xtb.feishu.cn/docx/JBsidACDVojhCaxFQLbcCVbsnAc?from=from_copylink]
*VTS Project Report starts
||
*
||
*
|-

|-
|Pengqi Li
||
*Consistency of TAO and LayerCAM
** Change TAO from input to final conv layer and obtain more consistency.(Aishell:0.93 in any model)
||
*
||
*
|-

|-
|Wan Lin
||
* NS: downsampling is not useful
* share speaker meeting in Friday
||
*
||
*
|-

|-
|Tianhao Wang
||
* AudioSep (CLAP) 5-mix exps:
** text-query: SDR=4.978, SI-SDR=1.972
** audio-query: SDR=6.907, SI-SDR=5.058
** This results with the loudness limitation
||
* AudioSep (CLAP) without loudness limitation
* Project things
||
*
|-

|-
|Xiaoxue Luo
||
*Comparative experiment between AudioSep and baseline system(CLIPSep)
*Prepare the report
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*reproduce 5-mix speech Separation results：
**pit：2-mix：16.04 ；5-mix：6.87
**conditional：5-mix：5.38（40 epoch）
||
*
||
*
|-

|-
|Junhui Chen
||
* NS：speaker detection （method survey & debug）
* get sick
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* SocioDojo (still worse than Nasdaq100 baseline)
** Change information sources, from the perspective of the report generated by LLM, more new information sources will be referenced.
** Prompt Actuator to consider current cash ratio before investing (with out this, the asset ratio goes up to 100%, which leads to high risks, still running)
* Read some papers about integrating time series into LLM
||
*
||
*
|-

|-
|Wenqiang Du
||
* Prepare data,code and environment for Pro.Mijiti
||
*
||
*
|-

|-
|Yang Wei
||
* Train text enroll KWS model with Aibabel training data. Not work.
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Whisper-largev3 finetuning
** Freezing 20 layers of encoder achieved 9.75 WER. Vanilla finetuning 8.02 WER
||
*
||
*
|-
|Yue Gu
||
* seek suggestions from other authors. Many suggestions are conflicting, so I'm try to figure out the reasons and fix these issues.
||
*
||
*
|-
|-
|Qi Qu
||
* KWS:
** Text-enroll models exported to ONNX.
** C/JNI libs built based on ONNX models and ready for on-device test.
||
*
||
*
|-

2024-10-21

2024-10-21T10:55:40Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Primary School AI hand book (20-30)
||
*
||
*
|-

|-
|Lantian Li
||
* AI-Graph EN (25/50)
* Complete CSTR intro report （11.18)
||
*
||
*
|-

|-
|Ying Shi
||
* Cohort-Overlap ASR
** condition on real decode result
** Design stop criterion
* Cohort-Speech separation
** several configs for Dual-path model
* [https://z1et6d3xtb.feishu.cn/docx/X3C4dFRoKo3PATxvXWUc40LOnye?from=from_copylink group work ]
||
*
||
*
|-

|-
|Zhenghai You
||
* Weekly report
||
*
||
*
|-

|-
|Junming Yuan
||
* The result of feat-mask/time-mask MT-HuBERT [https://z1et6d3xtb.feishu.cn/docx/IXBzdx2OvoDbvLxBLmKcjGJZnvb]
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*Verify VSR data
*Finish Data Verification Report
*ICL work(CER: 47.87% < CER: 51.08%)
*Time Mask matters[https://z1et6d3xtb.feishu.cn/docx/JBsidACDVojhCaxFQLbcCVbsnAc?from=from_copylink]
||
*
||
*
|-

|-
|Pengqi Li
||
* Complete the final report of the doctoral innovation project(School)
* Exploring the Consistency of TAO and LayerCAM Results on different models and datasets.
** Conclusion and hypothesis[https://z1et6d3xtb.feishu.cn/docx/Elh0d3t2RoEcUOxoIh2cBQG5nCc]
||
*
||
*
|-

|-
|Wan Lin
||
* help VSR data verification
* experiment in voxblink2 [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
* adjust the code of AudioSep (CLAP) to support multi-mix and audio-query (in training)
* some project testing
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*AudioSep reproduction
**evaluate the performance of AudioSep
**comparative experiment between AudioSep and baseline system(CLIPSep)
***adjusting the code
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*conditional chain 2-mix results reproduction（sisidr: 10.714 -> 15.6）
*model quantization finial version submission
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* SocioDojo Llama 3.1 8B investment task
** acc return is about 10% below nasdaq 100 index
||
* add more professional information source, such as WSJ (current is Tweets Trending, which is too entertainment-oriented)
* control the BUY/SELL amount of Actuator (current investments ratio is too high)
* reproduce other Multi Agent investment pipeline such as FinAgent or FinRobot
||
*
|-

|-
|Wenqiang Du
||
* Participated in an AI competition
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Whisper finetuning on sagalee
** with encoder frozen, whisper-large-v3 (20.5 WER)
* Finetuning LLM
** Finetuned Qwen2.5-0.5B on conversation dataset translated from English to Oromo
*
||
*
|-
|Yue Gu
||
* write the cover letter
* design a new speaker adaptation framework
||
*
||
*
|-
|-
|Qi Qu
||
* AED:
** New CED-based classifiers deployed onto devices, yielding acceptable performance.
* KWS:
** Quantization and format conversion of production models for deployment on embedded device w/ NPU. Default quantization mode leads to unacceptable loss of precision. Will try hybrid quantization.
** Text-enrollment KWS: some dynamic dimensions misinterpreted as constant duration exportation to ONNX.
||
*
||
*
|-

2024-10-21

2024-10-21T10:53:56Z

Linwan：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Primary School AI hand book (20-30)
||
*
||
*
|-

|-
|Lantian Li
||
* AI-Graph EN (25/50)
* Complete CSTR intro report （11.18)
||
*
||
*
|-

|-
|Ying Shi
||
* Cohort-Overlap ASR
** condition on real decode result
** Design stop criterion
* Cohort-Speech separation
** several configs for Dual-path model
* [https://z1et6d3xtb.feishu.cn/docx/X3C4dFRoKo3PATxvXWUc40LOnye?from=from_copylink group work ]
||
*
||
*
|-

|-
|Zhenghai You
||
* Weekly report
||
*
||
*
|-

|-
|Junming Yuan
||
* The result of feat-mask/time-mask MT-HuBERT [https://z1et6d3xtb.feishu.cn/docx/IXBzdx2OvoDbvLxBLmKcjGJZnvb]
||
*
||
*
|-

|-
|Xiaolou Li
||
*
||
*
||
*
|-

|-
|Zehua Liu
||
*Verify VSR data
*Finish Data Verification Report
*ICL work(CER: 47.87% < CER: 51.08%)
*Time Mask matters[https://z1et6d3xtb.feishu.cn/docx/JBsidACDVojhCaxFQLbcCVbsnAc?from=from_copylink]
||
*
||
*
|-

|-
|Pengqi Li
||
* Complete the final report of the doctoral innovation project(School)
* Exploring the Consistency of TAO and LayerCAM Results on different models and datasets.
** Conclusion and hypothesis[https://z1et6d3xtb.feishu.cn/docx/Elh0d3t2RoEcUOxoIh2cBQG5nCc]
||
*
||
*
|-

|-
|Wan Lin
||
* experiment in voxblink2 [https://z1et6d3xtb.feishu.cn/docx/MxBNdPbLao0tsoxkBVCcUgUoneh?from=from_copylink]
||
*
||
*
|-

|-
|Tianhao Wang
||
* adjust the code of AudioSep (CLAP) to support multi-mix and audio-query (in training)
* some project testing
||
*
||
*
|-

|-
|Xiaoxue Luo
||
*AudioSep reproduction
**evaluate the performance of AudioSep
**comparative experiment between AudioSep and baseline system(CLIPSep)
***adjusting the code
||
*
||
*
|-

|-
|Zhenyu Zhou
||
*conditional chain 2-mix results reproduction（sisidr: 10.714 -> 15.6）
*model quantization finial version submission
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* SocioDojo Llama 3.1 8B investment task
** acc return is about 10% below nasdaq 100 index
||
* add more professional information source, such as WSJ (current is Tweets Trending, which is too entertainment-oriented)
* control the BUY/SELL amount of Actuator (current investments ratio is too high)
* reproduce other Multi Agent investment pipeline such as FinAgent or FinRobot
||
*
|-

|-
|Wenqiang Du
||
* Participated in an AI competition
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Turi
||
* Whisper finetuning on sagalee
** with encoder frozen, whisper-large-v3 (20.5 WER)
* Finetuning LLM
** Finetuned Qwen2.5-0.5B on conversation dataset translated from English to Oromo
*
||
*
|-
|Yue Gu
||
* write the cover letter
* design a new speaker adaptation framework
||
*
||
*
|-
|-
|Qi Qu
||
* AED:
** New CED-based classifiers deployed onto devices, yielding acceptable performance.
* KWS:
** Quantization and format conversion of production models for deployment on embedded device w/ NPU. Default quantization mode leads to unacceptable loss of precision. Will try hybrid quantization.
** Text-enrollment KWS: some dynamic dimensions misinterpreted as constant duration exportation to ONNX.
||
*
||
*
|-