cslt Wiki - 用户贡献 [zh-cn]

2022-10-24

2022-10-24T10:58:55Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Homonet experiments with MNIST: for generaion model
* ICASSP papers
||
*
||
*
|-

|-
|Lantian Li
||
* Homo loss on SID
* Qiang's Paper
||
* ICASSP papers
||
*
|-

|-
|Ying Shi
||
* Homonet on aishell
* Homonet on Google speech command
||
* Continue on Homonet
||
*
|-

|-
|Chen Chen
||
* paper
* code, data for dataset release [http://cchen.cslt.org/mvs/ web]
||
* paper
* check code, data
||
*
|-

|-
|Pengqi Li
||
* update related work of other domain [https://z1et6d3xtb.feishu.cn/docx/doxcn5QLpYfgqhCxvuwteU854mb Outline]
||
* review and experiment
||
*
|-

|-
|Zixi Yan
||
* Graduation thesis
||
*
||
*
|-

|-
|Haoyu Jiang
||
* pick enroll audio and face
* graduation thesis
||
*
||
*
|-

|-
|Renmiao Chen
||
* pick enroll audio
* writing paper
||
* Finish paper
||
*
|-
|-
|Wenqiang Du
||
*
||
*
||
*
|-
|-
|Wan Lin
||
* Experiments
||
*
||
*
|-
|-
|Tianhao Wang
||
* Sunine following up: Large-margin fine-tuning strategy
||
*
||
*
|-
|Xipin Wei
||
* The experiment of mutil-track music generation
* The paper for icassp
||
* Project Summary and Report
* A fresh look at the music generation paper
||
*
|-

2022-10-24

2022-10-24T10:58:14Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Homonet experiments with MNIST: for generaion model
* ICASSP papers
||
*
||
*
|-

|-
|Lantian Li
||
* Homo loss on SID
* Qiang's Paper
||
* ICASSP papers
||
*
|-

|-
|Ying Shi
||
* Homonet on aishell
* Homonet on Google speech command
||
* Continue on Homonet
||
*
|-

|-
|Chen Chen
||
* paper
* code, data for dataset release [http://cchen.cslt.org/mvs/ web]
||
* paper
* check code, data
||
*
|-

|-
|Pengqi Li
||
* update related work of other domain [https://z1et6d3xtb.feishu.cn/docx/doxcn5QLpYfgqhCxvuwteU854mb Outline]
||
* review and experiment
||
*
|-

|-
|Zixi Yan
||
* Graduation thesis
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Extract embedding
* Graduation thesis
||
*
||
*
|-

|-
|Renmiao Chen
||
* pick enroll audio
* writing paper
||
*
||
*
|-
|-
|Wenqiang Du
||
*
||
*
||
*
|-
|-
|Wan Lin
||
* Experiments
||
*
||
*
|-
|-
|Tianhao Wang
||
* Sunine following up: Large-margin fine-tuning strategy
||
*
||
*
|-
|Xipin Wei
||
* The experiment of mutil-track music generation
* The paper for icassp
||
* Project Summary and Report
* A fresh look at the music generation paper
||
*
|-

2022-10-17

2022-10-17T10:50:19Z

Jianghaoyu：

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

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

|-
|Ying Shi
||
* prepare for ICASSP 2023
||
* homomorphic loss for each layer of current model
* mixup for transformer based model
* finish the paper
||
*
|-

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

|-
|Pengqi Li
||
* finished gradient based methods [https://z1et6d3xtb.feishu.cn/docx/doxcn5QLpYfgqhCxvuwteU854mb Outline]
||
* Experiments and review
||
*
|-

|-
|Zixi Yan
||
* Graduation thesis
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Extract embedding
* Graduation thesis
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|-
|Wenqiang Du
||
* Prepare papers
||
*
||
*
|-
|-
|Wan Lin
||
* Experiments
||
*
||
*
|-
|-
|Tianhao Wang
||
* How do deep speaker models treat silence and noises
||
* Sunine following up
||
*
|-
|Xipin Wei
||
* The experiment of mutil-track music generation
* The paper for icassp
||
* The experiment of mutil-track music generation
* The paper for icassp
||
*
|-

2022-10-10

2022-10-10T10:40:44Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Literature review for production model
* Review for TASLP
||
*
||
*
|-

|-
|Lantian Li
||
* APT-Lab progress
* Hard trials (derivation and listening)
||
* Overview paper
||
*
|-

|-
|Ying Shi
||
* Experiments and paper for icassp 2023
||
* continue on icassp 2023
||
*
|-

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

|-
|Pengqi Li
||
* Experiment and summary of gradient based methods [https://z1et6d3xtb.feishu.cn/docx/doxcn5QLpYfgqhCxvuwteU854mb Outline]
||
* finish it
||
*
|-

|-
|Zixi Yan
||
* Graduation thesis
* Work report
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Extract embedding
* Process the data
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* Generate LiRAVD
* Extract embedding and compute score
||
* Finish paper writing
||
*
|-
|-
|Wenqiang Du
||
* Translation overview
*
||
*
||
*
|-
|-
|Wan Lin
||
*
||
*
||
*
|-
|-
|Tianhao Wang
||
*
||
*
||
*
|-
|Xipin Wei
||
* The experiment of mutil-track music generation
||
* The experiment of mutil-track music generation
||
*
|-

2022-10-03

2022-10-03T10:48:42Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Review of Uyghr/Kazakh/Kryz ASR Chinese version done
||
*
||
*
|-

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

|-
|Ying Shi
||
* Finish my PhD proposal
* start experiments about speech engrave
||
* verify speech engrave on clean data
||
*
|-

|-
|Chen Chen
||
* Train ASR model on GRID and test WER
* Finish VCA-GAN experiments
* Prepare weekly-reading report
||
* Human hearing test
* WER
||
*
|-

|-
|Pengqi Li
||
*
||
* finish gradient based methods
||
*
|-

|-
|Zixi Yan
||
* Modify the paper
* Graduation thesis
||
*
||
*
|-

|-
|Haoyu Jiang
||
* data VAD
* Graduation thesis
||
*
||
*
|-

|-
|Renmiao Chen
||
* Get result for MOBIO
* pre-process for data
* Completed part of the paper writing.[http://index.cslt.org/mediawiki/images/e/e7/LiRAVD_Low_information_Real_world_Audio_Visual_Dataset_V0.1.pdf LiRAVD_draft_V0.1]
||
* Get result from all data
* Complete the first draft.
||
*
|-
|-
|Wenqiang Du
||
* Some project cooperation
||
*
||
*
|-
|-
|Wan Lin
||
*
||
*
||
*
|-
|-
|Tianhao Wang
||
* collate the experiment results and summarize the time mask method
||
*
||
*
|-
|Xipin Wei
||
* The music generation experiment of mutil-track-instruments
||
* The music generation experiment of mutil-track-instruments
||
*
|-

2022-09-26

2022-09-26T10:54:03Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Review low-resource ASR
||
* Complete the review
||

|-

|-
|Lantian Li
||
* Proposals on
** music generation
** binary speaker embedding
** acoustic-aware learning
||
* Hard trials paper...
||
*
|-

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

|-
|Chen Chen
||
* Finish draft
* pre-process CMLR data
||
* Train ASR model on GRID and test WER
* Train VTS model on CMLR single spk
* Train VCA-GAN
* Prepare weekly-reading report
||
*
|-

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

|-
|Zixi Yan
||
* Revise paper
* make a resume
||
*
||
*
|-

|-
|Haoyu Jiang
||
* weekly report
* Prepare the environment of Wenet
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* Finish data collection
* Finish CLLR score fusion
* Try the maskFace [http://index.cslt.org/mediawiki/images/5/5c/220926-CRM.pdf pdf]
||
* Finish tools for get LiRAVD
* Extract embedding from LiRAVD and get results
* Complete the remaining benchmarks
||
*
|-
|-
|Wenqiang Du
||
* Some project cooperation
||
*
||
*
|-
|-
|Wan Lin
||
*
||
*
||
*
|-
|-
|Tianhao Wang
||
* postgraduate recommendation
* time-aligned mask
||
* finish and summarize time-aligned mask
||
*
|-
|Xipin Wei
||
* Read the music generation documents
* The scheme of mutil-track-instruments
||
* The scheme of mutil-track-instruments
||
*
|-

Weekly reading

2022-09-23T12:21:48Z

Jianghaoyu：

'''清华大学语音语言中心内部学习会

'''时间：每周五晚19:30'''

'''地点： 1区303'''

{| class="wikitable"
! Date !! Speaker!! Title !! Materials
|-
| || || PPT模板 ||[[媒体文件:Weeklyreading_template.rar]]
|-
| 2021/04/01 ||Haoran Sun || Zeus code regularization ||[[媒体文件:代码规范.pdf]]
|-
| 2021/05/20 ||Chen Chen || Overview of speech enhancement|| [[媒体文件:Speech_enhancement.pdf]]
|-
| 2021/05/27 ||Di Wang || Secret of 'hard trials' || [[媒体文件:Secret_of_hard_trials.pdf]]
|-
| 2021/06/10 ||Jingxin Shen ||Expriments about thermal to RGB face synthesis with cycleGan and pix2pix || [[媒体文件:Expriments about thermal to RGB face synthesis with cycleGan and pix2pix.pdf]]
|-
| 2021/06/17 ||Yang Zhang || NIPS2020: Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect || [[媒体文件:long-tail.pdf]]
|-
| 2021/07/08 ||Tiankai Zhi || Some experiments on stargan ||[[媒体文件:Some experiments on stargan.pdf]]
|-
| 2021/07/15 ||Jiao Han || MG experiments based on ASV system || [[媒体文件:MG experiments based on ASV system..pptx]]
|-
| 2021/07/22 ||Zixi Yan & Sirui Li || Unsupervised Speech Recognition || [[媒体文件:Unsupervised_Speech_Recognition.pdf]]
|-
| 2021/07/29 ||Pengqi Li || A Simulation Study on 􏰛􏰜 Ro􏰛bust MAML || [[媒体文件:A Simulation Study on 􏰛􏰜 Ro􏰛bust MAML.pdf]]
|-
| 2021/08/12 ||Qingyang Zhu || Noise-aware method for Speech Enhancement || [[媒体文件:Noise-aware method for Speech Enhancement.pdf]]
|-
| 2021/08/12 ||Weida Liang || Unsupervised Audio-Visual Synthesis via Exemplar Autoencoders || [[媒体文件:Bi-weekly_report_Liangwd.pdf]]
|-
| 2021/08/19 ||Di Wang || Inter Dataset Variability Compensation || [[媒体文件:Inter_dataset_variability_compensation.pdf]]
|-
| 2021/09/02 ||Tiankai Zhi || One Shot VC || [[媒体文件:One_shot_VC.pdf]]
|-
| 2021/09/09 ||Jingxin Shen || Thermal Speaking || [[媒体文件:Thermal_Speaking_2021.pdf]]
|-
| 2021/09/23 ||Sirui Li & Zixi Yan || Wav2vec-U Experimental Report || [[媒体文件:Wav2vec-U_experimental_report.pdf ‎]]
|-
| 2021/10/20 ||Renmiao Chen || Is Someone Speaking? || [[媒体文件:Is_Someone_Speaking_Exploring_Long-term_Temporal_Features.pdf ‎]]
|-
| 2021/10/28 ||Chen Chen || WenetSpeech Introduction || [[媒体文件:WenetSpeech_Dataset_Introduction.pdf ‎]]
|-
| 2021/11/10 ||Weida Liang || Cycle-loss Exemplar Autoencoder || [[媒体文件:Cycle-loss_Exemplar_Autoencoder.pdf ‎]]
|-
| 2021/11/17 ||吾买尔江 || Modulation Spectrum || [[媒体文件:Modulation_Spectrum.pdf ‎]]
|-
| 2021/11/24 ||Chen Chen || S-DCCRN || [[媒体文件:S-DCCRN_pdf.pdf ‎]]
|-
| 2021/12/01 ||Pengqi Li || GuidedMix: An on-the-fly data augmentation approach for robust speaker recognition system || [[媒体文件:201201-GuidedMix-LPQ.pdf ‎]]
|-
| 2021/12/08 ||Renmiao Chen || Multimodal preson verification || [[媒体文件:Multimodal_preson_verification.pdf]]
|-
| 2021/12/15 ||Ruihai Hou || Crossmodal clustered contrastive learning: Grounding of spoken language to gesture || [[媒体文件:Crossmodal_clustered_contrasti.pdf]]
|-
| 2021/12/29 ||Zixi Yan || Capsules Network || [[媒体文件:Capsules_Network.pdf]]
|-
| 2022/01/05 ||Sirui Li || Self-Supervised Learning for speech recognition with Intermediate layer supervision || [[媒体文件:SSL with Intermediate layer supervision.pdf]]
|-
| 2022/01/12 ||Weida Liang || FragmentVC || [[媒体文件:FragmentVC.pdf]]
|-
| 2022/01/19 ||Haoyu Jiang || Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video || [[媒体文件:Multi-modality_Associative_Bridging_through_Memory.pdf]]
|-
| 2022/02/14 || || Interspeech 2021 Review || [[媒体文件:Interspeech_paper_review_min.pdf]]
|-
| 2022/02/16 ||Chen Chen || Audio Visual HuBERT || [[媒体文件:AVHuBERT.pdf]]
|-
| 2022/03/04 ||Pengqi Li || Study of Visualization || [[媒体文件:Visualization.pdf]]
|-
| 2022/03/11 ||Renmiao Chen || Can audio-visual integration strengthen robustness under multimodal attacks? || [[媒体文件:Audio-Visual_Robustness_Under_Multimodal_Attacks.pdf]]
|-
| 2022/03/11 ||吾买尔江 || Signal Separation || [[媒体文件:Signal_Separation.pdf]]
|-
| 2022/03/18 ||Chen Chen || Overview on Lip Reading and Audio-visual Speech Recognition || [[媒体文件:LipReadingAndAVSR.pdf]]
|-
| 2022/04/01 ||Ruihai Hou || Scalable Identity-Oriented Speech Retrieval || [[媒体文件:Scalable_Identity-Oriented_Speech_Retrieval.pdf]]
|-
| 2022/04/08 ||Zixi Yan || Wav2vec related papers share || [[媒体文件:Wav2vec_related_papers.pdf]]
|-
| 2022/04/22 ||Sirui Li || Speech-Based Language Modelling || [[媒体文件:Speech-Based Language Modelling.pdf]]
|-
| 2022/04/29 ||Haoyu Jiang || Models of Speaker Recognition || [[媒体文件:Models_of_Speaker_Recognition.pdf]]
|-
| 2022/05/13 ||Chen Chen || Audio-visual Representation Learning || [[媒体文件:Audio_visual_representation_learning.pdf]]
|-
| 2022/05/20 ||Haoran Sun || ||
|-
| 2022/05/27 ||Pengqi Li || The important ”feature” for speaker recognition || [[媒体文件:The important ”feature” for speaker recognition.pdf]]
|-
| 2022/06/10 ||Zixi Yan || Paper Share || [[媒体文件:Paper_share_yzx0610.pdf]]
|-
| 2022/06/24 ||Renmiao Chen || Transformer in multimodal || [[媒体文件:Transformer_in_multimodal.pdf]]
|-
| || || ICASSP 2022 review || [[媒体文件:ICASSP2022_review.pdf]] [[媒体文件:ICASSP-2022-readinglist.pdf]]
|-
| 2022/07/04 ||Chen Chen || Video to Speech papers || [[媒体文件:VTS_cc.pdf]]
|-
| 2022/07/08 ||Ruihai Hou || ICASSP 2022 review (part) || [[媒体文件:Weeklyreading_hrh.pdf]]
|-
| 2022/07/15 ||Sirui Li || Towards End-to-end Unsupervised Speech Recognition || [[媒体文件:Towards_End_to_end_Unsupervised_Speech_Recognition.pdf]]
|-
| 2022/07/22 ||Wan Lin || AutoED: Text-independent unsupervised speaker recognition Model|| [[媒体文件:AutoED_spk_reg.pdf]]
|-
| 2022/07/29 ||Haoyu Jiang || ArcFace_iQIYI-VID || [[媒体文件:ArcFace_iQIYI-VID.pdf]]
|-
| 2022/08/05 ||Chen Chen || Recent advance in VTS task || [[媒体文件:RecentVTS.pdf]]
|-
| 2022/08/12 ||Tianhao Wang || Extremal Perturbations || [[媒体文件:Extremal_perturbations.pdf]]
|-
| 2022/08/19 ||Renmiao Chen || The correlation of face and vioce || [[媒体文件:The_correlation_of_face_and_vioce_CRM.pdf]]
|-
| 2022/09/02 ||Zixi Yan || Non-Contrastive Self-supervised Learning || [[媒体文件:Non_contrastive_Self_supervised_Learning.pdf]]
|-
| 2022/09/09 ||Sirui Li || Low Resource Speech Recognition || [[媒体文件:Low_Resource_Speech_Recognition_lsr_0909.pdf]]
|-
| 2022/09/16 ||Xipin Wei || Controllable Multi-style Music Generation Model based on simple Contrastive Learning || [[媒体文件:Controllable_Multi_style_Music_Generation_Model_based_on_simple_Contrastive_learning.pdf]]
|-
| 2022/09/23 ||Haoyu Jiang || Audio Visual Learning || [[媒体文件:Audio_Visual_Learning.pdf]]
|-
| 2022/09/30 ||Wan Lin || ||
|-
| 2022/10/07 ||Tianhao Wang || ||
|-
| 2022/10/21 ||Chen Chen || ||
|-
| 2022/10/28 ||Pengqi Li || ||
|-
| 2022/11/04 ||Renmiao Chen || ||
|-
|}

[[Old readings|Past Events]]

Weekly reading

2022-09-23T12:21:29Z

Jianghaoyu：

'''清华大学语音语言中心内部学习会

'''时间：每周五晚19:30'''

'''地点： 1区303'''

{| class="wikitable"
! Date !! Speaker!! Title !! Materials
|-
| || || PPT模板 ||[[媒体文件:Weeklyreading_template.rar]]
|-
| 2021/04/01 ||Haoran Sun || Zeus code regularization ||[[媒体文件:代码规范.pdf]]
|-
| 2021/05/20 ||Chen Chen || Overview of speech enhancement|| [[媒体文件:Speech_enhancement.pdf]]
|-
| 2021/05/27 ||Di Wang || Secret of 'hard trials' || [[媒体文件:Secret_of_hard_trials.pdf]]
|-
| 2021/06/10 ||Jingxin Shen ||Expriments about thermal to RGB face synthesis with cycleGan and pix2pix || [[媒体文件:Expriments about thermal to RGB face synthesis with cycleGan and pix2pix.pdf]]
|-
| 2021/06/17 ||Yang Zhang || NIPS2020: Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect || [[媒体文件:long-tail.pdf]]
|-
| 2021/07/08 ||Tiankai Zhi || Some experiments on stargan ||[[媒体文件:Some experiments on stargan.pdf]]
|-
| 2021/07/15 ||Jiao Han || MG experiments based on ASV system || [[媒体文件:MG experiments based on ASV system..pptx]]
|-
| 2021/07/22 ||Zixi Yan & Sirui Li || Unsupervised Speech Recognition || [[媒体文件:Unsupervised_Speech_Recognition.pdf]]
|-
| 2021/07/29 ||Pengqi Li || A Simulation Study on 􏰛􏰜 Ro􏰛bust MAML || [[媒体文件:A Simulation Study on 􏰛􏰜 Ro􏰛bust MAML.pdf]]
|-
| 2021/08/12 ||Qingyang Zhu || Noise-aware method for Speech Enhancement || [[媒体文件:Noise-aware method for Speech Enhancement.pdf]]
|-
| 2021/08/12 ||Weida Liang || Unsupervised Audio-Visual Synthesis via Exemplar Autoencoders || [[媒体文件:Bi-weekly_report_Liangwd.pdf]]
|-
| 2021/08/19 ||Di Wang || Inter Dataset Variability Compensation || [[媒体文件:Inter_dataset_variability_compensation.pdf]]
|-
| 2021/09/02 ||Tiankai Zhi || One Shot VC || [[媒体文件:One_shot_VC.pdf]]
|-
| 2021/09/09 ||Jingxin Shen || Thermal Speaking || [[媒体文件:Thermal_Speaking_2021.pdf]]
|-
| 2021/09/23 ||Sirui Li & Zixi Yan || Wav2vec-U Experimental Report || [[媒体文件:Wav2vec-U_experimental_report.pdf ‎]]
|-
| 2021/10/20 ||Renmiao Chen || Is Someone Speaking? || [[媒体文件:Is_Someone_Speaking_Exploring_Long-term_Temporal_Features.pdf ‎]]
|-
| 2021/10/28 ||Chen Chen || WenetSpeech Introduction || [[媒体文件:WenetSpeech_Dataset_Introduction.pdf ‎]]
|-
| 2021/11/10 ||Weida Liang || Cycle-loss Exemplar Autoencoder || [[媒体文件:Cycle-loss_Exemplar_Autoencoder.pdf ‎]]
|-
| 2021/11/17 ||吾买尔江 || Modulation Spectrum || [[媒体文件:Modulation_Spectrum.pdf ‎]]
|-
| 2021/11/24 ||Chen Chen || S-DCCRN || [[媒体文件:S-DCCRN_pdf.pdf ‎]]
|-
| 2021/12/01 ||Pengqi Li || GuidedMix: An on-the-fly data augmentation approach for robust speaker recognition system || [[媒体文件:201201-GuidedMix-LPQ.pdf ‎]]
|-
| 2021/12/08 ||Renmiao Chen || Multimodal preson verification || [[媒体文件:Multimodal_preson_verification.pdf]]
|-
| 2021/12/15 ||Ruihai Hou || Crossmodal clustered contrastive learning: Grounding of spoken language to gesture || [[媒体文件:Crossmodal_clustered_contrasti.pdf]]
|-
| 2021/12/29 ||Zixi Yan || Capsules Network || [[媒体文件:Capsules_Network.pdf]]
|-
| 2022/01/05 ||Sirui Li || Self-Supervised Learning for speech recognition with Intermediate layer supervision || [[媒体文件:SSL with Intermediate layer supervision.pdf]]
|-
| 2022/01/12 ||Weida Liang || FragmentVC || [[媒体文件:FragmentVC.pdf]]
|-
| 2022/01/19 ||Haoyu Jiang || Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video || [[媒体文件:Multi-modality_Associative_Bridging_through_Memory.pdf]]
|-
| 2022/02/14 || || Interspeech 2021 Review || [[媒体文件:Interspeech_paper_review_min.pdf]]
|-
| 2022/02/16 ||Chen Chen || Audio Visual HuBERT || [[媒体文件:AVHuBERT.pdf]]
|-
| 2022/03/04 ||Pengqi Li || Study of Visualization || [[媒体文件:Visualization.pdf]]
|-
| 2022/03/11 ||Renmiao Chen || Can audio-visual integration strengthen robustness under multimodal attacks? || [[媒体文件:Audio-Visual_Robustness_Under_Multimodal_Attacks.pdf]]
|-
| 2022/03/11 ||吾买尔江 || Signal Separation || [[媒体文件:Signal_Separation.pdf]]
|-
| 2022/03/18 ||Chen Chen || Overview on Lip Reading and Audio-visual Speech Recognition || [[媒体文件:LipReadingAndAVSR.pdf]]
|-
| 2022/04/01 ||Ruihai Hou || Scalable Identity-Oriented Speech Retrieval || [[媒体文件:Scalable_Identity-Oriented_Speech_Retrieval.pdf]]
|-
| 2022/04/08 ||Zixi Yan || Wav2vec related papers share || [[媒体文件:Wav2vec_related_papers.pdf]]
|-
| 2022/04/22 ||Sirui Li || Speech-Based Language Modelling || [[媒体文件:Speech-Based Language Modelling.pdf]]
|-
| 2022/04/29 ||Haoyu Jiang || Models of Speaker Recognition || [[媒体文件:Models_of_Speaker_Recognition.pdf]]
|-
| 2022/05/13 ||Chen Chen || Audio-visual Representation Learning || [[媒体文件:Audio_visual_representation_learning.pdf]]
|-
| 2022/05/20 ||Haoran Sun || ||
|-
| 2022/05/27 ||Pengqi Li || The important ”feature” for speaker recognition || [[媒体文件:The important ”feature” for speaker recognition.pdf]]
|-
| 2022/06/10 ||Zixi Yan || Paper Share || [[媒体文件:Paper_share_yzx0610.pdf]]
|-
| 2022/06/24 ||Renmiao Chen || Transformer in multimodal || [[媒体文件:Transformer_in_multimodal.pdf]]
|-
| || || ICASSP 2022 review || [[媒体文件:ICASSP2022_review.pdf]] [[媒体文件:ICASSP-2022-readinglist.pdf]]
|-
| 2022/07/04 ||Chen Chen || Video to Speech papers || [[媒体文件:VTS_cc.pdf]]
|-
| 2022/07/08 ||Ruihai Hou || ICASSP 2022 review (part) || [[媒体文件:Weeklyreading_hrh.pdf]]
|-
| 2022/07/15 ||Sirui Li || Towards End-to-end Unsupervised Speech Recognition || [[媒体文件:Towards_End_to_end_Unsupervised_Speech_Recognition.pdf]]
|-
| 2022/07/22 ||Wan Lin || AutoED: Text-independent unsupervised speaker recognition Model|| [[媒体文件:AutoED_spk_reg.pdf]]
|-
| 2022/07/29 ||Haoyu Jiang || ArcFace_iQIYI-VID || [[媒体文件:ArcFace_iQIYI-VID.pdf]]
|-
| 2022/08/05 ||Chen Chen || Recent advance in VTS task || [[媒体文件:RecentVTS.pdf]]
|-
| 2022/08/12 ||Tianhao Wang || Extremal Perturbations || [[媒体文件:Extremal_perturbations.pdf]]
|-
| 2022/08/19 ||Renmiao Chen || The correlation of face and vioce || [[媒体文件:The_correlation_of_face_and_vioce_CRM.pdf]]
|-
| 2022/09/02 ||Zixi Yan || Non-Contrastive Self-supervised Learning || [[媒体文件:Non_contrastive_Self_supervised_Learning.pdf]]
|-
| 2022/09/09 ||Sirui Li || Low Resource Speech Recognition || [[媒体文件:Low_Resource_Speech_Recognition_lsr_0909.pdf]]
|-
| 2022/09/16 ||Xipin Wei || Controllable Multi-style Music Generation Model based on simple Contrastive Learning || [[媒体文件:Controllable_Multi_style_Music_Generation_Model_based_on_simple_Contrastive_learning.pdf]]
|-
| 2022/09/23 ||Haoyu Jiang || Audio_Visual_Learning || [[媒体文件:Audio_Visual_Learning.pdf]]
|-
| 2022/09/30 ||Wan Lin || ||
|-
| 2022/10/07 ||Tianhao Wang || ||
|-
| 2022/10/21 ||Chen Chen || ||
|-
| 2022/10/28 ||Pengqi Li || ||
|-
| 2022/11/04 ||Renmiao Chen || ||
|-
|}

[[Old readings|Past Events]]

文件:Audio Visual Learning.pdf

2022-09-23T12:20:33Z

Jianghaoyu：

2022-09-19

2022-09-19T10:52:20Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Purify AIGraph 3rd part
* Feedback to AIBook review
* Review work for Interspeech doctorial forum and several journal papers
* Slides for speech course
||
*
||
*
|-

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

|-
|Ying Shi
||
* PhD research proposal
* aishell course video
* Few-shot kws training
||
* research proposal ...
||
*
|-

|-
|Chen Chen
||
* Finish processing & annotating data
* Try VCAGAN, Lip2Wav, xTS training
* Finish preparing training data for VCAGAN, Lip2Wav, xTS
* Start draft
||
* train models
* finish Chinese [https://demo.hedgedoc.org/LDgt1VGhRAKjYz7Dzid-WA?view draft]
||
*
|-

|-
|Pengqi Li
||
* Gradient-based methods
||
*
||
*
|-

|-
|Zixi Yan
||
* Experimental data environment arrangement
||
*
||
*
|-

|-
|Sirui Li
||
* End-to-end unsupervised ASR
* make a resume
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Check LiRAVD data
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|-
|Wenqiang Du
||
* Minority speech recognition paper
* release asr model
||
*
|-
|-
|Wan Lin
||
*
||
*
||
*
|-
|-
|Tianhao Wang
||
* leave-one-out method (based on time-domain)
* postgraduate recommendation
||
*
||
*
|-
|Xipin Wei
||
* research speech CONTROLLABLE MULTI-STYLE MUSIC GENERATION MODEL BASED ON SIMPLE CONTRASTIVE LEARNING
||
* 1.model training;
* 2.experiment
||
*
|-

2022-09-12

2022-09-12T10:55:31Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Polish AI-Graph
* ISCSLP shuffle paper
||
*
||
*
|-

|-
|Lantian Li
||
* hard trials and shuffle papers.
||
*
||
*
|-

|-
|Ying Shi
||
* outline of my research proposal
* training data for multi-lingual kws
* the final aishell course
||
* write research proposal
* finish muli-lingual kws training and test on real test data(jiuming)
||
*
|-

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

|-
|Pengqi Li
||
* gradient-based methods(integrated gradient(IG), LRP(1/2))
||
* Experiments and summary
||
*
|-

|-
|Zixi Yan
||
* LiRAVD data collection
||
*
||
*
|-

|-
|Sirui Li
||
* weekly report
* submit paper
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Check LiRAVD data
* Find more people to collect
||
*
||
*
|-

|-
|Renmiao Chen
||
* add new functions for collect web
* audit data
||
* audit data
* prepare for pipeline
||
*
|-
|-
|Wenqiang Du
||
* Minority speech recognition paper
* Debug big model training for Aibabel
||
*
||
*
|-
|-
|Wan Lin
||
* finish paper
||
*
||
*
|-
|-
|Tianhao Wang
||
*
||
*
||
*
|-
|Xipin Wei
||
*
||
*
||
*
|-

2022-09-05

2022-09-05T10:55:14Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Simplify AI-graph
* CNSRC paper (part work)
||
*
||
*
|-

|-
|Lantian Li
||
* integrate paper on hard trials (fast SVM).
* review CNC papers.
||
*
||
*
|-

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

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

|-
|Pengqi Li
||
* Investigating interpretability libraries
* Study interpretability in text classification
||
* gradient-based methods(integrated gradient(IG), LRP, DeepLiFT)
||
*
|-

|-
|Zixi Yan
||
* Prepare papers to share
* LiRAVD data collection
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Check LiRAVD data
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|-
|Wenqiang Du
||
* aishell KALDI course
* Minority speech recognition paper
||
*
||
*
|-
|-
|Wan Lin
||
* Editor paper
||
*
||
*
|-

2022-08-29

2022-08-29T10:57:48Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* AI graph online resource done.
* Resume the work on the hard trials paper

||
*
||
*
|-

|-
|Lantian Li
||
* hard trials of CNC.E (SVM training...)
* review CNC series.
||
*
||
*
|-

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

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

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

|-
|Zixi Yan
||
* Prepare papers to share
* kaldi-cslt
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Test on AveRobot and Voxceleb1
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|-
|Wenqiang Du
||
* aishell KALDI course
* Minority speech recognition paper
* Some project cooperation
||
*
||
*
|-
|-
|Wan Lin
||
* Some Experiment
* Paper writing
||
*
||
*
|-

2022-08-22

2022-08-22T10:49:56Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* AI graph, online resource, part 4, nearly done (8 chapters missing)
* Design efficient computation for micro meganetic equation

||
*
||
*
|-

|-
|Lantian Li
||
* hard trials of CNC.E (SVM training...)
* trifles of BUPT projects
||
*
||
*
|-

|-
|Ying Shi
||
* fix and re-config server ...
* fix bug of transformer kws
||
* continue work on transformer kws
||
*
|-

|-
|Chen Chen
||
* Help with data-collect tools
* Train xts on multi speaker dependent and independent task
||
* Retrain xts model or hifigan to match hparam
* Support data-collect progress
||
*
|-

|-
|Pengqi Li
||
* Conference presentation ppt and poster
||
* presentation record
* max activation analysis
||
*
|-

|-
|Zixi Yan
||
* Mongolian Kaldi-cslt project
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Data collection test
* Data set download
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|-
|Wenqiang Du
||
* Some project cooperation
||
*
||
*
|-
|-
|Wan Lin
||
*
||
*
||
*
|-

2022-08-15

2022-08-15T11:02:21Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* AI-graph online resource, 3rd part done.
||
*
||
*
|-

|-
|Lantian Li
||
* Simulation on hard trials.
||
*
||
*
|-

|-
|Ying Shi
||
* transformer kws done waiting for run.
* fix server
* aishell course
||
*
||
*
|-

|-
|Chen Chen
||
* Reproduce VTS method [https://demo.hedgedoc.org/TjDwlDO2QJ2PQ55WRBShuw?view doc]
* Help with audit tools
||
* Add post-process to our dataset
||
*
|-

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

|-
|Zixi Yan
||
* Pre-training and fine-tuning process for SSAST project
||
*
||
*
|-

|-
|Sirui Li
||
* Revise paper
||
* more experiments
||
*
|-

|-
|Haoyu Jiang
||
* Benchmark
* Data collection test
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* Finish the collection pipeline
||
* Refine the collection pipeline
||
*
|-
|-
|Wenqiang Du
||
*
||
*
||
*
|-
|-
|Wan Lin
||
*
||
*
||
*
|-

2022-08-15

2022-08-15T11:02:05Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* AI-graph online resource, 3rd part done.
||
*
||
*
|-

|-
|Lantian Li
||
* Simulation on hard trials.
||
*
||
*
|-

|-
|Ying Shi
||
* transformer kws done waiting for run.
* fix server
* aishell course
||
*
||
*
|-

|-
|Chen Chen
||
* Reproduce VTS method [https://demo.hedgedoc.org/TjDwlDO2QJ2PQ55WRBShuw?view doc]
* Help with audit tools
||
* Add post-process to our dataset
||
*
|-

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

|-
|Zixi Yan
||
* Pre-training and fine-tuning process for SSAST project
||
*
||
*
|-

|-
|Sirui Li
||
* Revise paper
||
*
||
*
|-

|-
|Haoyu Jiang
||
* benchmark
* data collection test
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* Finish the collection pipeline
||
* Refine the collection pipeline
||
*
|-
|-
|Wenqiang Du
||
*
||
*
||
*
|-
|-
|Wan Lin
||
*
||
*
||
*
|-

2022-08-08

2022-08-08T10:46:38Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
*AI-graph online resource (part 2 done).
*Some review work for HLT and OCOCOSDA.
||
*
||
*
|-

|-
|Lantian Li
||
*hard trials of CNC.E
||
*
||
*
|-

|-
|Ying Shi
||
*zeus kws tools coding
** THU energy kws model done
** google few shot keywords for any language (instance learning) done
** samsung transformer based location guided attention kws done(single head transformer)
* slide of aishell 7th course
||
* samsung transformer based location guided attention (multi-head)
* large scale kws training
||
*
|-

|-
|Chen Chen
||
* Weekly Reading report
* Collect News30minutes data [https://codimd.s3.shivering-isles.com/demo/uploads/3979c39f-7ef8-4752-8426-77ffadcae5bb.png img]
* Audit & collect web page demo
||
* Process News30minutes data
* collect open source vts code
||
*
|-

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

|-
|Zixi Yan
||
*
||
*
||
*
|-

|-
|Sirui Li
||
* Finish first draft of the paper
||
* Revise the paper
||
*
|-

|-
|Haoyu Jiang
||
* Compare AcrFace and Facenet
* Test AcrFace on Vox1
||
*
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|-
|Wenqiang Du
||
* Some project cooperation
||
*
||
*
|-
|-
|Wan Lin
||
*
||
*
||
*
|-

2022-08-01

2022-08-01T10:51:07Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* APSIPA hard trials paper
* AI graph electronic resource (chapter 1 done)
||
*
||
*
|-

|-
|Lantian Li
||
* Submit hard-trials paper
||
*
||
*
|-

|-
|Ying Shi
||
* aishell course video
* kws coding
||
* test code and prepare baseline
||
*
|-

|-
|Chen Chen
||
* [https://demo.hedgedoc.org/uUA45m4bTL-wFiESUy1VIA?view doc]
* Add SyncNet to pipeline
* Analyze drawbacks of current pipeline
||
* Reading recent two years paper on VTS
* Prepare and run pipeline
||
*
|-

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

|-
|Zixi Yan
||
*
||
*
||
*
|-

|-
|Sirui Li
||
* paper outline
* kaldi script comments: gmm-hmm
||
* paper
||
*
|-

|-
|Haoyu Jiang
||
* weekly reading
* tests of DeepFace
||
* update pipeline code
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Wan Lin
||
*
||
*
||
*
|-

Weekly reading

2022-07-29T12:42:32Z

Jianghaoyu：

'''清华大学语音语言中心内部学习会

'''时间：每周五晚19:30'''

'''地点： 1区303'''

{| class="wikitable"
! Date !! Speaker!! Title !! Materials
|-
| || || PPT模板 ||[[媒体文件:Weeklyreading_template.rar]]
|-
| 2021/04/01 ||Haoran Sun || Zeus code regularization ||[[媒体文件:代码规范.pdf]]
|-
| 2021/05/20 ||Chen Chen || Overview of speech enhancement|| [[媒体文件:Speech_enhancement.pdf]]
|-
| 2021/05/27 ||Di Wang || Secret of 'hard trials' || [[媒体文件:Secret_of_hard_trials.pdf]]
|-
| 2021/06/10 ||Jingxin Shen ||Expriments about thermal to RGB face synthesis with cycleGan and pix2pix || [[媒体文件:Expriments about thermal to RGB face synthesis with cycleGan and pix2pix.pdf]]
|-
| 2021/06/17 ||Yang Zhang || NIPS2020: Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect || [[媒体文件:long-tail.pdf]]
|-
| 2021/07/08 ||Tiankai Zhi || Some experiments on stargan ||[[媒体文件:Some experiments on stargan.pdf]]
|-
| 2021/07/15 ||Jiao Han || MG experiments based on ASV system || [[媒体文件:MG experiments based on ASV system..pptx]]
|-
| 2021/07/22 ||Zixi Yan & Sirui Li || Unsupervised Speech Recognition || [[媒体文件:Unsupervised_Speech_Recognition.pdf]]
|-
| 2021/07/29 ||Pengqi Li || A Simulation Study on 􏰛􏰜 Ro􏰛bust MAML || [[媒体文件:A Simulation Study on 􏰛􏰜 Ro􏰛bust MAML.pdf]]
|-
| 2021/08/12 ||Qingyang Zhu || Noise-aware method for Speech Enhancement || [[媒体文件:Noise-aware method for Speech Enhancement.pdf]]
|-
| 2021/08/12 ||Weida Liang || Unsupervised Audio-Visual Synthesis via Exemplar Autoencoders || [[媒体文件:Bi-weekly_report_Liangwd.pdf]]
|-
| 2021/08/19 ||Di Wang || Inter Dataset Variability Compensation || [[媒体文件:Inter_dataset_variability_compensation.pdf]]
|-
| 2021/09/02 ||Tiankai Zhi || One Shot VC || [[媒体文件:One_shot_VC.pdf]]
|-
| 2021/09/09 ||Jingxin Shen || Thermal Speaking || [[媒体文件:Thermal_Speaking_2021.pdf]]
|-
| 2021/09/23 ||Sirui Li & Zixi Yan || Wav2vec-U Experimental Report || [[媒体文件:Wav2vec-U_experimental_report.pdf ‎]]
|-
| 2021/10/20 ||Renmiao Chen || Is Someone Speaking? || [[媒体文件:Is_Someone_Speaking_Exploring_Long-term_Temporal_Features.pdf ‎]]
|-
| 2021/10/28 ||Chen Chen || WenetSpeech Introduction || [[媒体文件:WenetSpeech_Dataset_Introduction.pdf ‎]]
|-
| 2021/11/10 ||Weida Liang || Cycle-loss Exemplar Autoencoder || [[媒体文件:Cycle-loss_Exemplar_Autoencoder.pdf ‎]]
|-
| 2021/11/17 ||吾买尔江 || Modulation Spectrum || [[媒体文件:Modulation_Spectrum.pdf ‎]]
|-
| 2021/11/24 ||Chen Chen || S-DCCRN || [[媒体文件:S-DCCRN_pdf.pdf ‎]]
|-
| 2021/12/01 ||Pengqi Li || GuidedMix: An on-the-fly data augmentation approach for robust speaker recognition system || [[媒体文件:201201-GuidedMix-LPQ.pdf ‎]]
|-
| 2021/12/08 ||Renmiao Chen || Multimodal preson verification || [[媒体文件:Multimodal_preson_verification.pdf]]
|-
| 2021/12/15 ||Ruihai Hou || Crossmodal clustered contrastive learning: Grounding of spoken language to gesture || [[媒体文件:Crossmodal_clustered_contrasti.pdf]]
|-
| 2021/12/29 ||Zixi Yan || Capsules Network || [[媒体文件:Capsules_Network.pdf]]
|-
| 2022/01/05 ||Sirui Li || Self-Supervised Learning for speech recognition with Intermediate layer supervision || [[媒体文件:SSL with Intermediate layer supervision.pdf]]
|-
| 2022/01/12 ||Weida Liang || FragmentVC || [[媒体文件:FragmentVC.pdf]]
|-
| 2022/01/19 ||Haoyu Jiang || Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video || [[媒体文件:Multi-modality_Associative_Bridging_through_Memory.pdf]]
|-
| 2022/02/14 || || Interspeech 2021 Review || [[媒体文件:Interspeech_paper_review_min.pdf]]
|-
| 2022/02/16 ||Chen Chen || Audio Visual HuBERT || [[媒体文件:AVHuBERT.pdf]]
|-
| 2022/03/04 ||Pengqi Li || Study of Visualization || [[媒体文件:Visualization.pdf]]
|-
| 2022/03/11 ||Renmiao Chen || Can audio-visual integration strengthen robustness under multimodal attacks? || [[媒体文件:Audio-Visual_Robustness_Under_Multimodal_Attacks.pdf]]
|-
| 2022/03/11 ||吾买尔江 || Signal Separation || [[媒体文件:Signal_Separation.pdf]]
|-
| 2022/03/18 ||Chen Chen || Overview on Lip Reading and Audio-visual Speech Recognition || [[媒体文件:LipReadingAndAVSR.pdf]]
|-
| 2022/04/01 ||Ruihai Hou || Scalable Identity-Oriented Speech Retrieval || [[媒体文件:Scalable_Identity-Oriented_Speech_Retrieval.pdf]]
|-
| 2022/04/08 ||Zixi Yan || Wav2vec related papers share || [[媒体文件:Wav2vec_related_papers.pdf]]
|-
| 2022/04/22 ||Sirui Li || Speech-Based Language Modelling || [[媒体文件:Speech-Based Language Modelling.pdf]]
|-
| 2022/04/29 ||Haoyu Jiang || Models of Speaker Recognition || [[媒体文件:Models_of_Speaker_Recognition.pdf]]
|-
| 2022/05/13 ||Chen Chen || Audio-visual Representation Learning || [[媒体文件:Audio_visual_representation_learning.pdf]]
|-
| 2022/05/20 ||Haoran Sun || ||
|-
| 2022/05/27 ||Pengqi Li || The important ”feature” for speaker recognition || [[媒体文件:The important ”feature” for speaker recognition.pdf]]
|-
| 2022/06/10 ||Zixi Yan || Paper Share || [[媒体文件:Paper_share_yzx0610.pdf]]
|-
| 2022/06/24 ||Renmiao Chen || Transformer in multimodal || [[媒体文件:Transformer_in_multimodal.pdf]]
|-
| || || ICASSP 2022 review || [[媒体文件:ICASSP2022_review.pdf]] [[媒体文件:ICASSP-2022-readinglist.pdf]]
|-
| 2022/07/04 ||Chen Chen || Video to Speech papers || [[媒体文件:VTS_cc.pdf]]
|-
| 2022/07/08 ||Ruihai Hou || ICASSP 2022 review (part) || [[媒体文件:Weeklyreading_hrh.pdf]]
|-
| 2022/07/15 ||Sirui Li || Towards End-to-end Unsupervised Speech Recognition || [[媒体文件:Towards_End_to_end_Unsupervised_Speech_Recognition.pdf]]
|-
| 2022/07/22 ||Wan Lin || AutoED: Text-independent unsupervised speaker recognition Model|| [[媒体文件:AutoED_spk_reg.pdf]]
|-
| 2022/07/29 ||Haoyu Jiang || ArcFace_iQIYI-VID || [[媒体文件:ArcFace_iQIYI-VID.pdf]]
|-
| ||Chen Chen || ||
|-
| ||Renmiao Chen || ||
|-
| ||Ruihai Hou || ||
|-
| ||Zixi Yan || ||
|-
| ||Sirui Li || ||
|-
| ||Haoyu Jiang || ||
|-
|}

[[Old readings|Past Events]]

文件:ArcFace iQIYI-VID.pdf

2022-07-29T12:41:52Z

Jianghaoyu：

2022-07-25

2022-07-25T10:56:26Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* AI-graph online resource
* Submit PAMI paper
* Reformate hard-trials paper
* Formate CNSRC paper

||
*
||
*
|-

|-
|Lantian Li
||
*Paper on hard trials
||
*
||
*
|-

|-
|Ying Shi
||
* coding
* aishell course video
||
* finish coding
* transformer keyword spotting baseline
* instance keyword baseline
||
*
|-

|-
|Chen Chen
||
* [https://demo.hedgedoc.org/uUA45m4bTL-wFiESUy1VIA?view doc]
* Finish data_collector version 0.1
* Processed two mini batch
||
* Manually evaluate generated videos and finetune data_collector
||
*
|-

|-
|Pengqi Li
||
* study some post-hoc method
||
* review and summarize
||
*
|-

|-
|Zixi Yan
||
* Read SSAST: Self-Supervised Audio Spectrogram Transformer
* Wav2vec multi-layer feature combination research and system design
||
*
||
*
|-

|-
|Sirui Li
||
* sv task: use wav2vec hubert mfcc feature
||
* paper
||
*
|-

|-
|Haoyu Jiang
||
* Tests of InsightFace
||
* Solve face detection model
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* Determine our plan
* Finish audio_drived_data_collector version 0.1
* Anaylze some example
* Design strategies for collection
* [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/d8/220725-Audio_driven%E5%88%9D%E6%AD%A5%E6%83%B3%E6%B3%95.pdf conclusion & preliminary ideas]
||
* Finish video-drived collection data collector
||
*
|-
|-
|Wenqiang Du
||
* Some project cooperation
||
* Some project cooperation
* English acoustic model upgrade
||
*
|-

|-
|Wan Lin
||
* Test the method mentioned in the last report
* Papers on noise filtering
||
* Find ways to improve model adaptability
||
*
|-

2022-06-27

2022-06-27T10:18:43Z

Jianghaoyu：

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

|-
|Yunqi Cai
||
*
||
*
||
*
|-

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

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

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* ICASSP 2022 review
||
* Reproduce some VSR models
||
*
|-

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

|-
|Zixi Yan
||
*
||
*
||
*
|-

|-
|Sirui Li
||
* Review ICASSP 2022 paper
* Unsupervised ASR on TIMIT and Librispeech
||
* Go on unsupervised ASR
||
*
|-

|-
|Haoyu Jiang
||
* Review ICASSP 2022 paper
* AV-CNC face detecting
||
* Face verification test
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* Prepare for paper sharing
||
* Read some papers about speaker recognition
||
*
|-
|-
|Wenqiang Du
||
* ICASSP 2022 review
* Event detection experiment about Coughing sound
* Some project cooperation
||
*
||
*
|-

2022-06-13

2022-06-13T10:43:19Z

Jianghaoyu：

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

|-
|Yunqi Cai
||
*
||
*
||
*
|-

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

|-
|Ying Shi
||
* school project proposal
* baseline: Few shot kws
||
* continue on kws baseline
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* Review cnc code, write documents
||
* ICASSP review
||
*
|-

|-
|Pengqi Li
||
* PUFA report, code, model
||
* Augment and mask
||
*
|-

|-
|Zixi Yan
||
* datasets-CMU_Wilderness
* Preparation for Paper Sharing
||
*
||
*
|-

|-
|Sirui Li
||
* Unsupervised ASR experiments
||
* Unsupervised ASR experiments
||
*
|-

|-
|Haoyu Jiang
||
* Test on face verification
||
* Go on test
||
*
|-

|-
|Ruihai Hou
||
* prepare for the final exam
||
* prepare for the final exam
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|-
|Wenqiang Du
||
* Some project cooperation
* Research on new projects
||
* Some project cooperation
||
*
|-

2022-06-06

2022-06-06T11:00:57Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* AIGraph-4 (1/2)
* AIShell course recording
* TASLP paper ready for submission
||
* TASLP submission
* AIGraph-4 done
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (CN-Celeb3)
* PUFA report (1/2)
||
* PUFA delivery
||
*
|-

|-
|Ying Shi
||
* Location guided attention kws (Samsung's work in interspeech 2021)
* CN3
||
* kws baseline
||
*
|-

|-
|Haoran Sun
||
* quantitative evaluation for speaker embedding
* cycleflow code
||
* more explorations for speaker embedding
||
*
|-

|-
|Chen Chen
||
* CNCeleb data
||
* Update CNCeleb dataset toolkits & docs
* Course pres
||
*
|-

|-
|Pengqi Li
||
* PUFA report
* CN3
||
*
||
*
|-

|-
|Zixi Yan
||
* Preparation for Paper Sharing
* CNCeleb
||
*
||
*
|-

|-
|Sirui Li
||
* Generate phone-level alignment labels
* CNC3
||
*
||
*
|-

|-
|Haoyu Jiang
||
* CNCeleb data
||
*
||
*
|-

|-
|Ruihai Hou
||
* CNCeleb3 data
||
*
||
*
|-

|-
|Renmiao Chen
||
* Finish some course reports
||
* Finish course project and pre
* prepare for test
||
*
|-
|-
|Wenqiang Du
||
* Some project cooperation
* CN3
||
* aishell KALDI course
||
*
|-

2022-05-30

2022-05-30T10:48:43Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* AI-Graph Part3 done.
* Some revision on TASLP cycleflow paper
||
* AI-Graph part4
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (CN-Celeb3, INFO)
* Posdoc defense/trifle
||
* PUFA report
||
*
|-

|-
|Ying Shi
||
* finish kws RNNT coding
* Few shot keyword spotting in any language
||
* Location guided attention kws (Samsung's work in interspeech 2021)
* QbE
* tuning all the baseline
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* Collecting celeb data
||
* Processing celeb data
||
*
|-

|-
|Pengqi Li
||
*weekly reading
*PUFA report
||
*argument and detection
||
*
|-

|-
|Zixi Yan
||
* Tool script Refactoring
* Read ANALYZING THE ROBUSTNESS OF UNSUPERVISED SPEECH RECOGNITION
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Collecting celeb data
||
* Processing celeb data
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* do course project
* prepare for examination
||
* do course project
||
*
|-
|-
|Wenqiang Du
||
*
||
*
||
*
|-

2022-05-23

2022-05-23T10:54:19Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* AI-Graph Part3 (1/2) completed
* Keep on review for interpretation in ASR/SID
||
* AI-Graph Part3 (2/2)
* Keep on review for interpretation in ASR/SID
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

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

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

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* Course projects
* 1of3 website
* CNCeleb pipeline
||
* CNCeleb
* Course projects
||
*
|-

|-
|Pengqi Li
||
*Some project task
*PUFA report
||
*Finish PUFA report
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
* Tibetan speech recognition experiment based on WAV2VEC feature(debug)
* Read paper Improving Speech Recognition for Indic Languages using Language Model
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Face verification test
* CNCeleb
||
* Go on test
* CNCeleb
||
*
|-

|-
|Ruihai Hou
||
* concurrent testing of speaker-diarization
* calculate RT of speaker-diarization
* CNCeleb
||
* CNCeleb
||
*
|-

|-
|Renmiao Chen
||
*
||
*
||
*
|-
|Wenqiang Du
||
* Some project cooperation
||
* Some project cooperation
||
*
|-

2022-05-16

2022-05-16T10:41:13Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Graph-AI book
* Review paper for interpreability for speech processing
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

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

|-
|Ying Shi
||
* reproduce Google attention RNN-T system
||
* continue work on attention RNN-T
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

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

|-
|Pengqi Li
||
*Some project task
||
*Finish PUFA report
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
* Tibetan speech recognition experiment based on MFCC
* Tibetan speech recognition experiment based on WAV2VEC feature
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Finish speaker verification test
* Data preparation for face verification
||
*
||
*
|-

|-
|Ruihai Hou
||
* deliver the first version of segTool
* setup the experiment environment of LSH
||
*
||
*
|-

|-
|Renmiao Chen
||
* do course projects
||
* do course projects
||
*
|-
|Wenqiang Du
||
* aishell KALDI course
* Some project cooperation
||
* Continue aishell KALDI course
* Some project cooperation
* Research on abusive sound detection
||
*
|-

Weekly reading

2022-04-29T14:00:17Z

Jianghaoyu：

'''清华大学语音语言中心内部学习会

'''时间：每周五晚19:30'''

'''地点： 1区303'''

{| class="wikitable"
! Date !! Speaker!! Title !! Materials
|-
| 2021/04/01 ||Haoran Sun || Zeus code regularization ||[[媒体文件:代码规范.pdf]]
|-
| 2021/05/20 ||Chen Chen || Overview of speech enhancement|| [[媒体文件:Speech_enhancement.pdf]]
|-
| 2021/05/27 ||Di Wang || Secret of 'hard trials' || [[媒体文件:Secret_of_hard_trials.pdf]]
|-
| 2021/06/10 ||Jingxin Shen ||Expriments about thermal to RGB face synthesis with cycleGan and pix2pix || [[媒体文件:Expriments about thermal to RGB face synthesis with cycleGan and pix2pix.pdf]]
|-
| 2021/06/17 ||Yang Zhang || NIPS2020: Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect || [[媒体文件:long-tail.pdf]]
|-
| 2021/07/08 ||Tiankai Zhi || Some experiments on stargan ||[[媒体文件:Some experiments on stargan.pdf]]
|-
| 2021/07/15 ||Jiao Han || MG experiments based on ASV system || [[媒体文件:MG experiments based on ASV system..pptx]]
|-
| 2021/07/22 ||Zixi Yan & Sirui Li || Unsupervised Speech Recognition || [[媒体文件:Unsupervised_Speech_Recognition.pdf]]
|-
| 2021/07/29 ||Pengqi Li || A Simulation Study on 􏰛􏰜 Ro􏰛bust MAML || [[媒体文件:A Simulation Study on 􏰛􏰜 Ro􏰛bust MAML.pdf]]
|-
| 2021/08/12 ||Qingyang Zhu || Noise-aware method for Speech Enhancement || [[媒体文件:Noise-aware method for Speech Enhancement.pdf]]
|-
| 2021/08/12 ||Weida Liang || Unsupervised Audio-Visual Synthesis via Exemplar Autoencoders || [[媒体文件:Bi-weekly_report_Liangwd.pdf]]
|-
| 2021/08/19 ||Di Wang || Inter Dataset Variability Compensation || [[媒体文件:Inter_dataset_variability_compensation.pdf]]
|-
| 2021/09/02 ||Tiankai Zhi || One Shot VC || [[媒体文件:One_shot_VC.pdf]]
|-
| 2021/09/09 ||Jingxin Shen || Thermal Speaking || [[媒体文件:Thermal_Speaking_2021.pdf]]
|-
| 2021/09/23 ||Sirui Li & Zixi Yan || Wav2vec-U Experimental Report || [[媒体文件:Wav2vec-U_experimental_report.pdf ‎]]
|-
| 2021/10/20 ||Renmiao Chen|| Is Someone Speaking? || [[媒体文件:Is_Someone_Speaking_Exploring_Long-term_Temporal_Features.pdf ‎]]
|-
| 2021/10/28 ||Chen Chen || WenetSpeech Introduction || [[媒体文件:WenetSpeech_Dataset_Introduction.pdf ‎]]
|-
| 2021/11/10 ||Weida Liang || Cycle-loss Exemplar Autoencoder || [[媒体文件:Cycle-loss_Exemplar_Autoencoder.pdf ‎]]
|-
| 2021/11/17 ||吾买尔江 || Modulation Spectrum || [[媒体文件:Modulation_Spectrum.pdf ‎]]
|-
| 2021/11/24 ||Chen Chen || S-DCCRN || [[媒体文件:S-DCCRN_pdf.pdf ‎]]
|-
| 2021/12/01 ||Pengqi Li || GuidedMix: An on-the-fly data augmentation approach for robust speaker recognition system || [[媒体文件:201201-GuidedMix-LPQ.pdf ‎]]
|-
| 2021/12/08 ||Renmiao Chen || Multimodal preson verification || [[媒体文件:Multimodal_preson_verification.pdf]]
|-
| 2021/12/15 ||Ruihai Hou || Crossmodal clustered contrastive learning: Grounding of spoken language to gesture || [[媒体文件:Crossmodal_clustered_contrasti.pdf]]
|-
| 2021/12/29 ||Zixi Yan || Capsules Network || [[媒体文件:Capsules_Network.pdf]]
|-
| 2022/01/05 ||Sirui Li || Self-Supervised Learning for speech recognition with Intermediate layer supervision || [[媒体文件:SSL with Intermediate layer supervision.pdf]]
|-
| 2022/01/12 ||Weida Liang || FragmentVC || [[媒体文件:FragmentVC.pdf]]
|-
| 2022/01/19 ||Haoyu Jiang || Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video || [[媒体文件:Multi-modality_Associative_Bridging_through_Memory.pdf]]
|-
| 2022/02/14 || || Interspeech 2021 Review || [[媒体文件:Interspeech_paper_review_min.pdf]]
|-
| 2022/02/16 ||Chen Chen || Audio Visual HuBERT || [[媒体文件:AVHuBERT.pdf]]
|-
| 2022/03/04 ||Pengqi Li || Study of Visualization || [[媒体文件:Visualization.pdf]]
|-
| 2022/03/11 ||Renmiao Chen || Can audio-visual integration strengthen robustness under multimodal attacks? || [[媒体文件:Audio-Visual_Robustness_Under_Multimodal_Attacks.pdf]]
|-
| 2022/03/11 ||吾买尔江 || Signal Separation || [[媒体文件:Signal_Separation.pdf]]
|-
| 2022/03/18 ||Chen Chen || Overview on Lip Reading and Audio-visual Speech Recognition || [[媒体文件:LipReadingAndAVSR.pdf]]
|-
| 2022/04/01 ||Ruihai Hou || Scalable Identity-Oriented Speech Retrieval || [[媒体文件:Scalable_Identity-Oriented_Speech_Retrieval.pdf]]
|-
| 2022/04/08 ||Zixi Yan || ||
|-
| 2022/04/15 ||Sirui Li || Speech-Based Language Modelling || [[媒体文件:Speech-Based Language Modelling.pdf]]
|-
| 2022/04/22 ||Weida Liang || ||
|-
| 2022/04/29 ||Haoyu Jiang || Models of Speaker Recognition || [[媒体文件:Models_of_Speaker_Recognition.pdf]]
|-
| 2022/05/06 ||Chen Chen || ||
|-
| ||Pengqi Li || ||
|-
| ||Renmiao Chen || ||
|-
| ||Ruihai Hou || ||
|-
| ||Zixi Yan || ||
|-
| ||Sirui Li || ||
|-
| ||Weida Liang || ||
|-
| ||Haoyu Jiang || ||
|-
|}

[[Old readings|Past Events]]

文件:Models of Speaker Recognition.pdf

2022-04-29T13:59:13Z

Jianghaoyu：

2022-04-25

2022-04-25T11:05:59Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Keep on visualization review
||
* Complete the visualization review
* More on graphical AI
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC
* Posdoc report (4/5)
||
* Push CNCSRC (Template)
* PUFA project delivery
* Posdoc report (Done)
||
*
|-

|-
|Ying Shi
||
* investigate CNN channel [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=854 cvss]
||
* continue work on CNN
||
*
|-

|-
|Haoran Sun
||
* l1 adv loss
||
* subjective evaluation
||
*
|-

|-
|Chen Chen
||
* Review AVSR & LipReading papers
* Prepare course quiz & project
||
* Review AVSR & LipReading papers
* Pre-process LRW-1000 dataset and test pretrain model
||
*
|-

|-
|Pengqi Li
||
* Project
||
* Project (Done)
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
* Noss experimental system construction
||
*
||
*
|-

|-
|Sirui Li
||
* Prepare weekly reading report
* Generate lexicon with 10 Clusters
||
* Remove speaker information for phonetic classification
||
*
|-

|-
|Haoyu Jiang
||
* Read paper about these model
* Test on VGG model
||
* Go on test
||
*
|-

|-
|Ruihai Hou
||
* continue organizing the code structure for speaker diarization
* add time license
||
*
||
*
|-

|-
|Renmiao Chen
||
* Prepare course quiz & project
||
* Read some paper about cross-modal
||
*
|-

2022-04-25

2022-04-25T10:51:30Z

Jianghaoyu：

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

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC
* Posdoc report (4/5)
||
* Push CNCSRC (Template)
* PUFA project delivery
* Posdoc report (Done)
||
*
|-

|-
|Ying Shi
||
* investigate CNN channel [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=854 cvss]
||
* continue work on CNN
||
*
|-

|-
|Haoran Sun
||
* l1 adv loss
||
* subjective evaluation
||
*
|-

|-
|Chen Chen
||
* Review AVSR & LipReading papers
* Prepare course quiz & project
||
* Review AVSR & LipReading papers
* Pre-process LRW-1000 dataset and test pretrain model
||
*
|-

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

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
* Noss experimental system construction
||
*
||
*
|-

|-
|Sirui Li
||
* Prepare weekly reading report
* Generate lexicon with 10 Clusters
||
* Remove speaker information for phonetic classification
||
*
|-

|-
|Haoyu Jiang
||
* read paper about these model
* test on VGG model
||
* go on test
||
*
|-

|-
|Ruihai Hou
||
* continue organizing the code structure for speaker diarization
* add time license
||
*
||
*
|-

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

2022-04-18

2022-04-18T11:09:21Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Review paper on speech visalization
||
* Keep on visualization review paper
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (Toolkit/QA/ECAPA)
* Posdoc report (2/5)
* ICASSP 2022 presentation
||
* Push CNCSRC (Template)
* PUFA project delivery
* Posdoc report (Done)
|-

|-
|Ying Shi
||
* School project proposal
||
* back to zeus/kws
||
*
|-

|-
|Haoran Sun
||
* The dissertation
||
* Cycle paper
||
*
|-

|-
|Chen Chen
||
* Review AVSR & LipReading papers
||
* Review AVSR & LipReading papers
* Prepare course quiz & project
||
*
|-

|-
|Pengqi Li
||
* Project(1/3)
* study attention
||
* Project
* study methods of pooling related to attention
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
* Read the paper, What all do audio transformer models hear? Probing Acoustic Representations for language delivery and its structure
||
*
||
*
|-

|-
|Sirui Li
||
* ABX score for Librispeech
||
* Generate lexicon with CTC
||
*
|-

|-
|Haoyu Jiang
||
* Try to test the baseline with a uniform code
||
* Read papers about the baseline
||
*
|-

|-
|Ruihai Hou
||
* Organize the code structure for speaker diarization
||
*
||
*
|-

|-
|Renmiao Chen
||
* Prepare course quiz & project
||
* Prepare course quiz & project
* read some papers
||
*
|-

2022-04-18

2022-04-18T10:57:59Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Review paper on speech visalization
||
* Keep on visualization review paper
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (Toolkit/QA/ECAPA)
* Posdoc report (2/5)
* ICASSP 2022 presentation
||
* Push CNCSRC (Template)
* PUFA project delivery
* Posdoc report (Done)
|-

|-
|Ying Shi
||
* School project proposal
||
* back to zeus/kws
||
*
|-

|-
|Haoran Sun
||
* The dissertation
||
* Cycle paper
||
*
|-

|-
|Chen Chen
||
* Review AVSR & LipReading papers
||
* Review AVSR & LipReading papers
* Prepare course quiz & project
||
*
|-

|-
|Pengqi Li
||
* Project(1/3)
* study attention
||
* Project
* study methods of pooling related to attention
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
*
||
*
||
*
|-

|-
|Sirui Li
||
* ABX score for Librispeech
||
* Generate lexicon with CTC
||
*
|-

|-
|Haoyu Jiang
||
* Try to test the baseline with a uniform code
||
*
||
*
|-

|-
|Ruihai Hou
||
* Organize the code structure for speaker diarization
||
*
||
*
|-

|-
|Renmiao Chen
||
* Prepare course quiz & project
||
* Prepare course quiz & project
* read some papers
||
*
|-

2022-04-11

2022-04-11T10:48:51Z

Jianghaoyu：

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

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (refresh SOTA model)
* Complete Spoof overview
||
* Push CNCSRC
* PUFA project delivery
* Posdoc report
|-

|-
|Ying Shi
||
* Zeus/kws
** CNN ASR
** IBM Double AE
** THU energy model
** Google Rnn-t (in progress)
** QbE (in progress)
** 4 kaldi kws recipe(in progress)
||
* Verify CNN
* continue on zeus/kws
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* update cycleflow website
* review unsupervised AVSR papers
||
* write review
||
*
|-

|-
|Pengqi Li
||
* paper's web and code
||
* project
||
*
|-

|-
|Weida Liang
||
* web and code for paper
* Presentation
||
*
||
*
|-

|-
|Zixi Yan
||
* Wav2vec paper review preparation
* Cos sim experimental data collation
||
*
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Data preprocessing
* Learn the code for data loading
||
*
||
*
|-

|-
|Ruihai Hou
||
* continue the test on LSH
||
*
||
*
|-

|-
|Renmiao Chen
||
* do some work about OCR
||
* continue the task on OCR
* read papers
||
*
|-

2022-03-28

2022-03-28T10:54:09Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Interspeech refinement
* Keyword spotting review
||
* Keyword spotting review
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC
* INTERSPEECH 2022
||
* Push CNCSRC
* Spoof overview
* PUFA project delivery
|-

|-
|Ying Shi
||
* Continue work on Speech engrave (TXT convolution)
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* Prepare ASR/OCR model for ICPRMSR
* Reading paper of lip2wav
||
* Review recent papers about Lip Reading & AVSR
* Prepare ASR/OCR model for ICPRMSR
||
*
|-

|-
|Pengqi Li
||
* INTERSPEECH
||
* code, homepage for paper
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
* Cos sim experiment of WAV2VEC feature and MFCC feature
||
*
||
*
|-

|-
|Sirui Li
||
* Dictionary generation for true and pseudo-labeled
||
* Downstream ASR Task
||
*
|-

|-
|Haoyu Jiang
||
* Test on SOTA model
* Learn score normalization
||
* Go on test
* Test with s-norm
||
*
|-

|-
|Ruihai Hou
||
* Build experiment environment on the server
* Extract embeddings of 2793 speakers
||
*
||
*
|-

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

2022-03-21

2022-03-21T11:04:58Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Rewrite the TASLP RC paper
* Design new architecture for speech engrave
||
* Interspeech paper polishment
||
*
|-

|-
|Yunqi Cai
||
* continue proposals
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (Submission system and Leaderboard Open)
* PUFA project delivery [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=832 cvss]
* Sunine update
||
* Push CNCSRC
* INTERSPEECH 2022
|-

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

|-
|Haoran Sun
||
* experiments for cycle loss
* website of cycleflow
||
* paper
||
*
|-

|-
|Chen Chen
||
* Prepare weekly reading report
||
* Review Mandrain Lip Reading Datasets
||
*
|-

|-
|Pengqi Li
||
* more Experiments on visualization
||
* Interspeech
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
*
||
*
||
*
|-

|-
|Sirui Li
||
* Phoneme set discovery and dictionary generation
||
* dictionary generation and ASR task
||
*
|-

|-
|Haoyu Jiang
||
* Collect SOTA pre-training model and test on AV-CN-Celeb
||
* Go on test and collect
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* finished plda model
||
* test the SOTA model for face recognition
* explore the means to calculate the confidence of audio
* do some experiments for different confidence to fuse the audio and face
||
*
|-

}

2022-03-21

2022-03-21T11:00:46Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Rewrite the TASLP RC paper
* Design new architecture for speech engrave
||
* Interspeech paper polishment
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (Submission system and Leaderboard Open)
* PUFA project delivery [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=832 cvss]
* Sunine update
||
* Push CNCSRC
* INTERSPEECH 2022
|-

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

|-
|Haoran Sun
||
* experiments for cycle loss
* website of cycleflow
||
* paper
||
*
|-

|-
|Chen Chen
||
* Prepare weekly reading report
||
* Review Mandrain Lip Reading Datasets
||
*
|-

|-
|Pengqi Li
||
* more Experiments on visualization
||
* Interspeech
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
*
||
*
||
*
|-

|-
|Sirui Li
||
* Phoneme set discovery and dictionary generation
||
* Go on dictionary generation
||
*
|-

|-
|Haoyu Jiang
||
* Collecte SOTA pre-training model and test on AV-CN-Celeb
||
* Go on
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* finished plda model
||
* test the SOTA model for face recognition
* explore the means to calculate the confidence of audio
* do some experiments for different confidence to fuse the audio and face
||
*
|-

}

2022-03-14

2022-03-14T10:53:50Z

Jianghaoyu：

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

|-
|Yunqi Cai
||
* revise and submit NSFC project
||
*
||
*
|-

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

|-
|Ying Shi
||
* Speech engrave with alignment
* Speech engrave with enhancement loss [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/61/Engrave_recover_result.pdf here]
||
* Continue work on speech engrave: Design more smart mask mechanisms
||
*
|-

|-
|Haoran Sun
||
* results of CycleVC [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/05/CycleVCd128.pdf pdf]
* tools for vc
||
* paper
||
*
|-

|-
|Chen Chen
||
* Prepare report of Lip Reading & AVSR
||
* Reproduce experiments of reviewed methods
||
*
|-

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

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
* The WAV2VEC model trained by Librispeech dataset was used for Chinese Asr experiments
||
*
||
*
|-

|-
|Sirui Li
||
* Phoneme set discovery and dictionary generation
||
* Improve phoneme translation system
||
*
|-

|-
|Haoyu Jiang
||
* Data statistics of AV-CN-Celeb
||
* Design SOTA model test experiment
||
*
|-

|-
|Ruihai Hou
||
* Test top-N and speed on binary embedding
||
* Prepare paper sharing
||
*
|-

|-
|Renmiao Chen
||
* redo for MI and CKA
* achieve dePLDA
||
* improve dePLDA
* do some experiment for score fusion
|-

|}

文件:Dataset.zip

2022-03-08T08:33:46Z

Jianghaoyu：AV-CN-Celeb数据列表

AV-CN-Celeb数据列表

2022-03-07

2022-03-07T10:58:30Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Odyssey papers done
* Trans RC paper draft done
||
* More literature review for the Trans TC paper
||
*
|-

|-
|Yunqi Cai
||
* NSCF revising
||
*write popular science project
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (Release SR.eval and C-P map)
* Finish Odyssey paper
||
* PUFA project delivery
||
*
|-

|-
|Ying Shi
||
* Attention based Speech engrave
** adversarial learning
** Gaussian graver
** Garbage node training
* Speech engrave with alignment
** garbage node training
||
* Test Speech engrave with alignment
** search decoding
||
*
|-

|-
|Haoran Sun
||
* the odyssey paper
* cycle and adversarial training on AutoVC [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/14/CycleVC.pdf pdf]
||
* CycleVC adjustment
* Cycle loss plus adversarial loss on AutoVC
* experiments for RC paper
||
*
|-

|-
|Chen Chen
||
* Review papers about lip-reading & audio-visual speech recognization
* Do experimrnts of AV-HuBERT
||
* Review papers about lip-reading & audio-visual speech recognization
* Try finetune & pretrain of AV-HuBERT
||
*
|-

|-
|Pengqi Li
||
* experiments on visualization
||
* check and reconstruct experiments
||
*
|-

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
*
||
*
||
*
|-

|-
|Sirui Li
||
* Do experiments on MOSES system
||
* Prepare phrase-based MT training data
* train phrase-based MT
||
*
|-

|-
|Haoyu Jiang
||
* Finish speaker recognition training on AV-CNCeleb
||
* Do face recognition training on AV-CNCeleb
||
*
|-

|-
|Ruihai Hou
||
* test binary embedding performance (mAP, speed) on speaker retrieval task
||
* do some tests on AE
||
*
|-

|-
|Renmiao Chen
||
* learn and try to use dePLDA
||
* finish task of dePLDA
* prepare for sharing
|-

|}

2022-02-28

2022-02-28T10:40:55Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Investigation on IB/VC
* Odyssey paper
||
* Odyssey paper
||
*
|-

|-
|Yunqi Cai
||
* NCFS project
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (Update Sunine)
* Finish ASVSpoof response
* Polish C-P Map
||
* Odyssey paper
||
*
|-

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

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* Review papers about lip-reading & audio-visual speech recognization
* Done: Prepare data & environment for experiments of AV-HuBERT
||
* Review papers about lip-reading & audio-visual speech recognization
* Do experimrnts of AV-HuBERT
||
*
|-

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

|-
|Weida Liang
||
*
||
*
||
*
|-

|-
|Zixi Yan
||
* Asr experiments on different layers of multilingual W2V model
||
*
||
*
|-

|-
|Sirui Li
||
* Find and learn the mose system
||
* Train and test the mose system
||
*
|-

|-
|Haoyu Jiang
||
* Train the CN-Celeb baseline
||
* Go on training
* Prepare data
||
*
|-

|-
|Ruihai Hou
||
* finish speaker diarization interface and generate diarization figure
||
*
||
*
|-

|-
|Renmiao Chen
||
* test and adjust single-modality modal
||
* learn and use decoupled PLDA for cross-modal test
|-

|}

文件:Acc.pdf

2022-02-21T12:08:48Z

Jianghaoyu：

2022-02-21

2022-02-21T11:20:07Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Experiment on IB control with conditional model [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=wangd&step=view_request&cvssid=847], rough conclusions were obtained.
* Refine the AV speaker recognition theoretical part.
* Review for ICME.
||
* Complete ICME review
* VQMIVC reproduction, update with random mask
* Some missing papers treatment: (1) true nonlinear LDA (2) CycleFlow (3) Thermal-visual database
||
*
|-

|-
|Yunqi Cai
||
*NSFC Application
*Materials inverse design investigation
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (Data release and SR baseline)
* Submit Tencent AI Lab project
* Submit M2ASR concluding report
* Write ASVSpoof response
||
* Submit ASVSpoof response
* Finish Draft of C-P Map paper
||
*
|-

|-
|Ying Shi
||
* Speech engrave on overlap speech data
* M2ASR final report
||
* Speech engrave on overlap speech data
||
*
|-

|-
|Haoran Sun
||
* autoVC with cycle loss [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/16/Autovc-cyc.pdf pdf] [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/66/Pre.rar demo]
||
* cycle loss after adverserial training
* VQMIVC
||
*
|-

|-
|Chen Chen
||
* Review papers about lip-reading & audio-visual speech recognization
* Prepare data & environment for experiments of AV-Hubert
||
* <-- keep doing these tasks
||
*
|-

|-
|Pengqi Li
||
* collated the visualization methods that have been reproduced
* some scripts for baseline(cncsrc)
||
* study feature aggregation
||
*
|-

|-
|Weida Liang
||
* 3~6 spk cycle loss models on wav2vec+seq2seq model
* Rewrite paper and focus on cycle loss
||
* Finish paper framework
* Push test on WER scoring
||
*
|-

|-
|Zixi Yan
||
* Multi-language W2V model features were used for ASR experiments and compared with traditional MFCC features
||
* Asr experiments on different layers of multilingual W2V model
||
*
|-

|-
|Sirui Li
||
* Make an experiment plan
* Read the HuBERT paper and code
||
* Finish the hubert-U framework
||
*
|-

|-
|Haoyu Jiang
||
*Find the baseline for CN-Celeb speaker identification
||
*Train this baseline and find face recognition baseline
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* Check CKA
* Do experiment for gender
||
* Do experiment for cross-modal PLDA
|-

|}

2022-02-21

2022-02-21T10:42:11Z

Jianghaoyu：

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

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC (Data release and SR baseline)
* Submit Tencent AI Lab project
* Submit M2ASR concluding report
* Write ASVSpoof response
||
* Submit ASVSpoof response
* Finish Draft of C-P Map paper
||
*
|-

|-
|Ying Shi
||
* Speech engrave on overlap speech data
* M2ASR final report
||
* Speech engrave on overlap speech data
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* Review papers about lip-reading & audio-visual speech recognization
* Prepare data & environment for experiments of AV-Hubert
||
* <-- keep doing these tasks
||
*
|-

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

|-
|Weida Liang
||
* 3~6 spk cycle loss models on wav2vec+seq2seq model
* Rewrite paper and focus on cycle loss
||
* Finish paper framework
* Push test on WER scoring
||
*
|-

|-
|Zixi Yan
||
* Multi-language W2V model features were used for ASR experiments and compared with traditional MFCC features
||
* Asr experiments on different layers of multilingual W2V model
||
*
|-

|-
|Sirui Li
||
*
||
*
||
*
|-

|-
|Haoyu Jiang
||
*Find the baseline for CN-Celeb speaker identification
||
*Train this baseline and find more face recognition baseline
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-

|-
|Renmiao Chen
||
* Check CKA
||
*
|-

|}

文件:All high data.txt

2022-01-24T12:04:11Z

Jianghaoyu：

文件:Target video.txt

2022-01-24T12:03:48Z

Jianghaoyu：

文件:Face video.txt

2022-01-24T12:03:18Z

Jianghaoyu：

文件:Conf meta.txt

2022-01-24T12:02:10Z

Jianghaoyu：

2022-01-24

2022-01-24T11:03:54Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Reschedule the cycleFlow paper
* Keep on investigation for multi-modality information fusion
||
* Rewrite cycleFlow
||
*
|-

|-
|Yunqi Cai
||
*Investigate railway Bureau; the practical application scenario of intelligent inspection robot
*Prepare a report for Gusu Lab
||
* keep on intelligent sensor investigation
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC
* Submit final papers
* Prepare hard trials paper
||
* Go on hard trials paper
||
*
|-

|-
|Ying Shi
||
* investige forward attention [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=829 here]
||
* continue on forward attention
||
*
|-

|-
|Haoran Sun
||
* some experiments on AutoVC [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/1c/Autovc.pdf pdf]
||
* more experiments for cycle loss
||
*
|-

|-
|Chen Chen
||
* Experiments on kmeans and use label for clustering
* Experiments on # of phn kinds
* [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=cchen&step=view_request&cvssid=846 cvss]
||
* Check the experimrnt of label clustering
||
*
|-

|-
|Pengqi Li
||
* study representation learning(self-supervised learning)
* Using mel-spectrum and standard softmax on small data, models are trained
* Data preprocessing
||
* Visualization on a small models(mel-spectrum & MFCC)
* Implement RELAX
||
*
|-

|-
|Weida Liang
||
* Conduct wav2vec test
* Adjust andRun wav2vec+decoder model(training 40k/50k)
* Add experiment details to paper
||
* paper submission to Arxiv
||
*
|-

|-
|Zixi Yan
||
* Training supervised speech recognition models using wav2vec features
||
* Experiments with more data sets
||
*
|-

|-
|Sirui Li
||
* Extract MFCC features for GAN
* Learning Clustering Algorithms
||
* go on GAN experiment
||
*
|-

|-
|Haoyu Jiang
||
* Complete data merge
* Prepare group report
||
* Comparison of audio-video baseline
||
*
|-

|-
|Ruihai Hou
||
* Preproess data for the training of UIS-RNN
* Train the UIS-RNN model on small dataset
||
*
||
*
|-

|-
|Renmiao Chen
||
* Finish MI test.
* Finish CKA test.
||
*
|-

|}

2022-01-24

2022-01-24T11:02:12Z

Jianghaoyu：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Reschedule the cycleFlow paper
* Keep on investigation for multi-modality information fusion
||
* Rewrite cycleFlow
||
*
|-

|-
|Yunqi Cai
||
*Investigate railway Bureau; the practical application scenario of intelligent inspection robot
*Prepare a report for Gusu Lab
||
* keep on intelligent sensor investigation
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC
* Submit final papers
* Prepare hard trials paper
||
* Go on hard trials paper
||
*
|-

|-
|Ying Shi
||
* investige forward attention [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=829 here]
||
* continue on forward attention
||
*
|-

|-
|Haoran Sun
||
* some experiments on AutoVC [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/1c/Autovc.pdf pdf]
||
* more experiments for cycle loss
||
*
|-

|-
|Chen Chen
||
* Experiments on kmeans and use label for clustering
* Experiments on # of phn kinds
* [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=cchen&step=view_request&cvssid=846 cvss]
||
* Check the experimrnt of label clustering
||
*
|-

|-
|Pengqi Li
||
* study representation learning(self-supervised learning)
* Using mel-spectrum and standard softmax on small data, models are trained
* Data preprocessing
||
* Visualization on a small models(mel-spectrum & MFCC)
* Implement RELAX
||
*
|-

|-
|Weida Liang
||
* Conduct wav2vec test
* Adjust andRun wav2vec+decoder model(training 40k/50k)
* Add experiment details to paper
||
* paper submission to Arxiv
||
*
|-

|-
|Zixi Yan
||
* Training supervised speech recognition models using wav2vec features
||
* Experiments with more data sets
||
*
|-

|-
|Sirui Li
||
* Extract MFCC features for GAN
* Learning Clustering Algorithms
||
* go on GAN experiment
||
*
|-

|-
|Haoyu Jiang
||
* Complete data merge
* Prepare group report
||
* Comparison of audio-video data
||
*
|-

|-
|Ruihai Hou
||
* Preproess data for the training of UIS-RNN
* Train the UIS-RNN model on small dataset
||
*
||
*
|-

|-
|Renmiao Chen
||
* Finish MI test.
* Finish CKA test.
||
*
|-

|}