cslt Wiki - 用户贡献 [zh-cn]

2022-04-11

2022-04-11T10:44:41Z

Liangwd：

{| 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
||
*
||
*
||
*
|-

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

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

2022-03-28

2022-03-28T11:07:30Z

Liangwd：

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

|-
|Yunqi Cai
||
* Reports writing
||
*
||
*
|-

|-
|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
||
* INTERSPEECH
||
* code update
* homepage building
||
*
|-

|-
|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
||
* weighted score fusion
* score-weight score fusion
* SNR-weight score fusion
||
* OCR
* layer-SNR-weight score fusion
* find some reseach about recognition in information incompleteness
||
*
|-

文件:Map.jpg

2022-03-23T08:35:15Z

Liangwd：Liangwd上传“文件:Map.jpg”的新版本

文件:Map.jpg

2022-03-23T08:32:03Z

Liangwd：

文件:Map.png

2022-03-23T08:29:50Z

Liangwd：Liangwd上传“文件:Map.png”的新版本

文件:Map.png

2022-03-23T07:38:17Z

Liangwd：Liangwd上传“文件:Map.png”的新版本

文件:Map.png

2022-03-23T07:35:28Z

Liangwd：Liangwd上传“文件:Map.png”的新版本

文件:Map.png

2022-03-23T07:30:08Z

Liangwd：Liangwd上传“文件:Map.png”的新版本

文件:Map.png

2022-03-23T07:29:13Z

Liangwd：

Active Projects

2022-03-23T07:13:26Z

Liangwd：

=Active projects=

[[Deep_Speech_Factorization-2|Deep Speech Factorization (Phase 2)]]

[[Asr-project-nsfc|Multilingual Minorilanguage Automatic Speech Recognition (M2ASR)]]

[[AI 100 QA]]

=Paused projects=

[[Vivi-poem-generation|Vivi Poem]]

=Completed projects=

==Speech Processing==
[[Enhanced exemplar autoencoder with cycle consistency loss in any-to-one voice conversion]]

[[Deep Generative Factorization For Speech Signal(ICASSP21)]]

[[Flow-based Speech Analysis|Unsupervised speech factorization (ICASSP20)]]

[[CN-Celeb|CN-Celeb (ICASSP20)]]

[[Deep_Speaker_Feature_Learning|Deep Speaker Feature Learning]]

[[Deep_Speech_Factorization|Deep Speech Factorization (Phase I)]]

[[Speaker_Recognition_on_Trivial_events|Speaker Recognition on Trivial Events]]

[[Phonetic_Temporal_Neural_LID|Phonetic Temporal Neural Model for Language Identification]]

[[Asr-project-segment|Deep speaker segmentation]]

[[TTS-project-synthesis|Flexible speech synthesis]]

==Language Processing==

[[Vivi-translation|Vivi Neural translation]]

==Financial Processing==

[[racorn-k|Risk Aversion Corn-K]]

Active Projects

2022-03-23T07:13:13Z

Liangwd：/* Speech Processing */

2022-03-21

2022-03-21T11:07:28Z

Liangwd：

{| 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
||
* Speech engrave on MNIST
* Speech engrave on Speech data
||
* INTERSPEECH
||
*
|-

|-
|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
||
* paper on CycleAE
||
* website update
* code upload
||
*
|-

|-
|Zixi Yan
||
* Speaker recognition experiment was performed using WAV2VEC
||
*
||
*
|-

|-
|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

2022-03-21T11:06:42Z

Liangwd：

{| 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
||
* Speech engrave on MNIST
* Speech engrave on Speech data
||
* INTERSPEECH
||
*
|-

|-
|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
||
* paper on CycleVC
||
* website update
* code upload
||
*
|-

|-
|Zixi Yan
||
* Speaker recognition experiment was performed using WAV2VEC
||
*
||
*
|-

|-
|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
||
*
|-

}

2022-03-14

2022-03-14T11:06:07Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Keep on revising the TASLP paper
* More review on disentanglement
||
* Finish review disentanglement
||
*
|-

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

|-
|Lantian Li
||
* Push CNCSRC (Submission system, Leaderboard and Evaluation toolkit)
* PUFA project delivery
||
* Release CNCSRC Submission and Leaderboard
* PUFA project delivery
||
*
|-

|-
|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
||
* do more experiments on visualization
||
*
||
*
|-

|-
|Weida Liang
||
* various tests with GOP SCA MOSNet and CER scoring
* 4 Spk VC done
* modify paper
||
* try 6 Spk VC
* submit paper
||
*
|-

|-
|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
|-

|}

2022-03-14

2022-03-14T11:02:19Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Keep on revising the TASLP paper
* More review on disentanglement
||
* Finish review disentanglement
||
*
|-

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

|-
|Lantian Li
||
* Push CNCSRC (Submission system, Leaderboard and Evaluation toolkit)
* PUFA project delivery
||
* Release CNCSRC Submission and Leaderboard
* PUFA project delivery
||
*
|-

|-
|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
||
* do more experiments on visualization
||
*
||
*
|-

|-
|Weida Liang
||
* various tests with GOP SCA MOSNet and CER scoring
* 4 Spk VC done
* modify paper
||
* try 6 Spk VC
* submit paper for Interspeech
||
*
|-

|-
|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
|-

|}

2022-03-07

2022-03-07T11:11:16Z

Liangwd：

{| 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
||
* experiments on CycleVAE
* Check and finish paper framework [http://166.111.134.19:7777/liangwd/paper_final.html]
||
* finish Multi-speaker test
||
*
|-

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

|-
|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
|-

|}

2022-03-07

2022-03-07T11:04:28Z

Liangwd：

{| 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
||
* experiments on CycleVAE
* Check and finish paper framework
||
* finish Multi-speaker test
||
*
|-

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

|-
|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
|-

|}

2022-02-21

2022-02-21T11:31:01Z

Liangwd：

{| 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
||
* Never-before-seen test [http://166.111.134.19:7777/liangwd/paper.html]
* 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

2022-02-21T10:38:27Z

Liangwd：

{| 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
||
*
||
*
||
*
|-

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

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

|}

2022-01-24

2022-01-24T10:58:27Z

Liangwd：

{| 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
||
*
||
*
||
*
|-

|-
|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.
||
*
|-

|}

2022-01-17

2022-01-17T10:38:19Z

Liangwd：

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

|-
|Yunqi Cai
||
*Low-light image simulation and data preparation
*capsule network review
*Research plan guidance for interns
*Conceptual model of intelligent sensor
||
*
||
*
|-

|-
|Lantian Li
||
* Polish CNCSRC plan
* Write hard trials paper
||
* Finish hard trials paper
||
*
|-

|-
|Ying Shi
||
* Analysis FA of Speech engrave
* Speech engrave with position embedding [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=829 here]
||
* Analysis Speech engrave with position embedding
||
*
|-

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

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

|-
|Pengqi Li
||
* Read Paper (RELAX,RISE); Finish Demo about RISE
* Evaluate the importance maps with Deletion and Insertion
||
* Test MFCC
* Finish RELAX
||
*
|-

|-
|Weida Liang
||
* Paper sharing on any-to-any VC
* Finish training wav2vec model
* Ongoing wav2vec+AE model
||
* Finish all model training
* Test and comparison analysis
||
*
|-

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

|-
|Sirui Li
||
* Extract MFCC features for GAN
* Write a project application
||
* Go on GAN experiment
||
*
|-

|-
|Haoyu Jiang
||
*
||
*
||
*
|-

|-
|Ruihai Hou
||
* Read the UIS-RNN paper
* Run some tests on speaker diarization
||
* Try to train the UIS-RNN model
||
*
|-

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

|}

2022-01-10

2022-01-10T11:12:11Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Finish CNSRC challenge plan
* Deal with ICASSP response
* Keep on survey for multi-modal information fusion
||
* Keep on multi-modal technique review
||
*
|-

|-
|Yunqi Cai
||
* Capsnet generative model investigation
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC plan
* Make Real AM rebuttal
||
* Go on hard trials paper
||
*
|-

|-
|Ying Shi
||
* Speech engrave (text attend speech)
* attention visualization [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=829 here]
||
* Speech engrave v2
||
*
|-

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

|-
|Chen Chen
||
* Finish course thesis
* Test UASR with different phone symbol
||
* Figure out reason of the influence of symbol
* Test w2v2.0 feats with other NN instead of GAN
||
*
|-

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

|-
|Weida Liang
||
* Finish wav2vec+decoder model and do self-evaluation test
* evaluate the scale of network
||
* Finish the never-before seen test
* Paper sharing on Wednesday
||
*
|-

|-
|Zixi Yan
||
* Thchs30 speech recognition using Kaldi
* Try using the WAV2VEc feature in Kaldi speech recognition, modify make_mfcc.sh
||
*
||
*
|-

|-
|Sirui Li
||
* Compare the effect of wav2vec parameter tuning
* Prepare group report
||
* Extract Chinese features for GAN
||
*
|-

|-
|Haoyu Jiang
||
* Calculate the acc of each segment score
||
* Complete data merge
||
*
|-

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

|-
|Renmiao Chen
||
* Finish course task
||
* Finish pmi
|-

|}

2022-01-10

2022-01-10T11:04:53Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Finish CNSRC challenge plan
* Deal with ICASSP response
* Keep on survey for multi-modal information fusion
||
* Keep on multi-modal technique review
||
*
|-

|-
|Yunqi Cai
||
* Capsnet generative model investigation
||
*
||
*
|-

|-
|Lantian Li
||
* Push CNCSRC plan
* Make Real AM rebuttal
||
* Go on hard trials paper
||
*
|-

|-
|Ying Shi
||
* Speech engrave (text attend speech)
* attention visualization [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=829 here]
||
* Speech engrave v2
||
*
|-

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

|-
|Chen Chen
||
* Finish course thesis
* Test UASR with different phone symbol
||
* Figure out reason of the influence of symbol
* Test w2v2.0 feats with other NN instead of GAN
||
*
|-

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

|-
|Weida Liang
||
* Finish wav2vec+decoder model and do self-evaluation test
* evaluate the scale of network
||
* Finish the never-before seen test
||
*
|-

|-
|Zixi Yan
||
* Thchs30 speech recognition using Kaldi
* Try using the WAV2VEc feature in Kaldi speech recognition, modify make_mfcc.sh
||
*
||
*
|-

|-
|Sirui Li
||
* Compare the effect of wav2vec parameter tuning
* Prepare group report
||
* Extract Chinese features for GAN
||
*
|-

|-
|Haoyu Jiang
||
* Calculate the acc of each segment score
||
* Complete data merge
||
*
|-

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

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

|}

2022-01-03

2022-01-03T11:20:44Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Review multi-modal and multi-view literature
* Design lip2wav models (possibly based on GCN)
* Continuous construct theory for noisy linear flow and PCA
||
* Keep on multi-modal design
* CNSRC test plan
||
*
|-

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

|-
|Lantian Li
||
* Push CNCSRC plan
* Update Sunine toolkit [https://gitlab.com/csltstu/sunine]
||
* Go on hard trials paper
||
*
|-

|-
|Ying Shi
||
* m2asr
* speech engrave text attend speech
||
* speech engrave text attend speech
||
*
|-

|-
|Haoran Sun
||
* some modification on x-vector
||
* intorduce bottleneck into it
||
*
|-

|-
|Chen Chen
||
* Finish final exam
* Finish course projects
||
* 3 small course thesis
||
*
|-

|-
|Pengqi Li
||
* Prepare for final exam
||
* Final exam for a week
||
*
|-

|-
|Weida Liang
||
* Modify wav2vec+decoder model
||
* Finish training model
||
*
|-

|-
|Zixi Yan
||
* Try supervised speech recognition based on WAV2VEC
||
* Wav2vec supervised speech recognition system was built
* Multilingual WAV2VEC supervised recognition experiment was conducted
||
*
|-

|-
|Sirui Li
||
* Do wav2vec-u in Swedish
* Prepare bi-weekly report
||
* go on wav2vec-u
||
*
|-

|-
|Haoyu Jiang
||
* Recalculate FAR
* Divide the data into several parts
||
* Calculate the FAR of the divided data
* To complete the data partition
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-
*
|-
|Renmiao Chen
||
* Prepare for stochastic process final exam
||
* Finish the remaining homework
* Do some work
||
*
|-
|}

2022-01-03

2022-01-03T11:13:46Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Review multi-modal and multi-view literature
* Design lip2wav models (possibly based on GCN)
* Continuous construct theory for noisy linear flow and PCA
||
* Keep on multi-modal design
* CNSRC test plan
||
*
|-

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

|-
|Lantian Li
||
* Push CNCSRC plan
* Update Sunine toolkit [https://gitlab.com/csltstu/sunine]
||
* Go on hard trials paper
||
*
|-

|-
|Ying Shi
||
* m2asr
* speech engrave text attend speech
||
* speech engrave text attend speech
||
*
|-

|-
|Haoran Sun
||
* some modification on x-vector
||
* intorduce bottleneck into it
||
*
|-

|-
|Chen Chen
||
* Finish final exam
* Finish course projects
||
* 3 small course thesis
||
*
|-

|-
|Pengqi Li
||
* Prepare for final exam
||
* Final exam for a week
||
*
|-

|-
|Weida Liang
||
* Modify wav2vec+decoder model
||
* Finish training model
* Paper sharing on Wednesday
||
*
|-

|-
|Zixi Yan
||
* Try supervised speech recognition based on WAV2VEC
||
* Wav2vec supervised speech recognition system was built
* Multilingual WAV2VEC supervised recognition experiment was conducted
||
*
|-

|-
|Sirui Li
||
* Do wav2vec-u in Swedish
* Prepare bi-weekly report
||
* go on wav2vec-u
||
*
|-

|-
|Haoyu Jiang
||
* Recalculate FAR
* Divide the data into several parts
||
* Calculate the FAR of the divided data
* To complete the data partition
||
*
|-

|-
|Ruihai Hou
||
*
||
*
||
*
|-
*
|-
|Renmiao Chen
||
* Prepare for stochastic process final exam
||
* Finish the remaining homework
* Do some work
||
*
|-
|}

2021-12-27

2021-12-27T11:13:47Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Hard trails paper revised
* Investigate link between AE and flow in the linear case [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/91/Linear.png]
* Investigate audio visual pretraining
||
* Keep on neural PCA theory
||
*
|-

|-
|Yunqi Cai
||
* AE baseline
* Alignet & AE joint training for Infra to Visible domain transfer
* Gatenet for Visible and Infra latent code fusion [https://qw4sbuvrmj.feishu.cn/docs/doccnNaBy0EAyUTskPQvvN7kgWo]
||
*
||
*
|-

|-
|Lantian Li
||
* Plan CNCSRC stuffs.
* Maintain Sunine.
* Deliver projects.
* Modify patents.
||
* Go on Hard trials paper.
||
*
|-

|-
|Ying Shi
||
* m2asr Kirgiz check
||
* continue on speech engrave (text attend speech; HMM based attention)
||
*
|-

|-
|Haoran Sun
||
* some contrast experiment
||
* design the timbre encoder with a design similar to x-vector
* insert the new encoder into our four-encoder structure
||
*
|-

|-
|Chen Chen
||
* Do course project
* Organize Kirgiz data
||
* Do course project
* Prepare for stochastic process final exam
||
*
|-

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

|-
|Weida Liang
||
* Finish patent disclosure
* Update the project website and upload never_before_seen result[http://166.111.134.19:7777/liangwd/never_before_seen.html]
* Go on with seq2seq test
||
* Finish seq2seq test
* Update paper
||
*
|-

|-
|Zixi Yan
||
* Debug bugs encountered when using the fine-tuning model
||
*
||
*
|-

|-
|Sirui Li
||
* Adjust the parameters to use thchs30 training
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Sampling out pictures compute FAR
||
*
||
*
|-

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

|-
|Renmiao Chen
||
* Do course project
||
* Do course project
* Prepare for stochastic process final exam
||
*
|-

|}

2021-12-27

2021-12-27T11:09:16Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Hard trails paper revised
* Investigate link between AE and flow in the linear case [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/91/Linear.png]
* Investigate audio visual pretraining
||
* Keep on neural PCA theory
||
*
|-

|-
|Yunqi Cai
||
* AE baseline
* Alignet & AE joint training for Infra to Visible domain transfer
* Gatenet for Visible and Infra latent code fusion [https://qw4sbuvrmj.feishu.cn/docs/doccnNaBy0EAyUTskPQvvN7kgWo]
||
*
||
*
|-

|-
|Lantian Li
||
* Plan CNCSRC stuffs.
* Maintain Sunine.
* Deliver projects.
* Modify patents.
||
* Go on Hard trials paper.
||
*
|-

|-
|Ying Shi
||
* m2asr Kirgiz check
||
* continue on speech engrave (text attend speech; HMM based attention)
||
*
|-

|-
|Haoran Sun
||
* some contrast experiment
||
* design the timbre encoder with a design similar to x-vector
* insert the new encoder into our four-encoder structure
||
*
|-

|-
|Chen Chen
||
* Do course project
* Organize Kirgiz data
||
* Do course project
* Prepare for stochastic process final exam
||
*
|-

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

|-
|Weida Liang
||
* Finish patent disclosure
* Update the project website and upload never_before_seen result
* Go on with seq2seq test
||
* Finish seq2seq test
* Update paper
||
*
|-

|-
|Zixi Yan
||
* Debug bugs encountered when using the fine-tuning model
||
*
||
*
|-

|-
|Sirui Li
||
* Adjust the parameters to use thchs30 training
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Sampling out pictures compute FAR
||
*
||
*
|-

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

|-
|Renmiao Chen
||
* Do course project
||
* Do course project
* Prepare for stochastic process final exam
||
*
|-

|}

2021-12-20

2021-12-20T11:08:19Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Hard trials paper revision - on going
* ICASSP paper review done
||
* Hard trials paper reviewion - keep on
||
*
|-

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

|-
|Lantian Li
||
* Upload AI course exam questions.
* Merge ECAPA-TDNN and Auto-LR into Sunine.
* Submit ETM TASLP response.
||
* Clean up PUFA data and build cross-channel system.
* Take charge of CNCSRC.
* Exps of hard trials.
||
*
|-

|-
|Ying Shi
||
* Some analyse about fncmd and speech engrave [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=829 cvss]
* Prepare huawei retrain
||
* Consider about HMM-based attention mechanism
||
*
|-

|-
|Haoran Sun
||
* add contrastive loss
||
* short-term ib dimension adjustment
* speaker encoder adjustment
||
*
|-

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

|-
|Pengqi Li
||
* a little analysis about aamsoftmax on cam && saliency map on image domain
* homework
||
*
||
*
|-

|-
|Weida Liang
||
* baseline result for not-before seen test
* framework for wav2vec model
||
* test for wave2vec model
* patent writing
||
*
|-

|-
|Zixi Yan
||
* Preparation for sharing about capsule
* Revise the thesis opening report
||
*
||
*
|-

|-
|Sirui Li
||
* Unsupervised experiment of thchs30
* Revise the thesis opening report
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Compute the cosine distance
* Revise the thesis opening report
||
*
||
*
|-

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

|}

2021-12-13

2021-12-12T16:52:40Z

Liangwd：

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

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

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

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

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

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

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

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* Finish training for not-ever-seen speaker on baseline AE and cycle model
* Build the framework of wav2vec model
||
* Full test on baseline & cycle model
* More details need to be discussed on wav2vec model
||
*
|-

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

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

|-
|Haoyu Jiang
||
*
||
*
||
*
|-

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

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

|}

2021-12-06

2021-12-05T17:01:28Z

Liangwd：

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

|-
|Yunqi Cai
||
*review papers about CQDs
*Verify the deconvolution of infrared and visible faces
*Verify infrared and visible image fusion based on GLOW model
*Arrange research plans for interns
||
*
||
*
|-

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

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

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

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

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

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* Finish the first version on improved exemplar autoencoder with cycle loss
* Rethink the theory analysis part
||
* Test on never-before-seen speaker conversion
* Review the code of wav2vec, StarGAN and PPG based GAN
||
*
|-

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

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

|-
|Haoyu Jiang
||
*
||
*
||
*
|-

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

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

|}

2021-11-29

2021-11-29T01:33:25Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Anti-spoof paper
* Some paper review
||
* Complete anti-spoof paper
* Prepare a talk on over-tuniung
||
*
|-

|-
|Yunqi Cai
||
* Prepare frame alignment project plans for interns
* Intelligent infrared detector working platform
* CQDs infrared detector investigation
||
*
||
*
|-

|-
|Lantian Li
||
* SOTA models for hard trials (ECAPA-TDNN and GE2E).
* Study AI/ML book.
||
* Exps of hard trials.
||
*
|-

|-
|Ying Shi
||
* Speech engrave train&test
||
* improve speech engrave
||
*
|-

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

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

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

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* Speaker Classification Test
||
* Further test on classification
* First version of the expected paper
||
*
|-

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

|-
|Sirui Li
||
* Comparative experiment of WSJ, Tibetan and Thchs30
||
*
||
*
|-

|-
|Haoyu Jiang
||
* Preparing the enroll data set
* Preparing the Tracker tool
||
* Sampling of CNCeleb dataset
||
*
|-

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

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

|}

2021-11-15

2021-11-15T11:10:07Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Spoof paper almost done
||
* Spoof paper cleaning
* Hard trials paper
||
*
|-

|-
|Yunqi Cai
||
* Completed THS2021 data preprocessing, image feature extraction, and baseline
||
*
||
*
|-

|-
|Lantian Li
||
* Complete hard trials paper v1.
||
*
||
* Go on preparing my defence.
|-

|-
|Ying Shi
||
* make a comparison between fncmd with new methods
* find some cross-modality methods(Cross modality attention)
||
* Implement Cross modality attention
||
*
|-

|-
|Haoran Sun
||
* speaker and robustness test for CycleFlow-spk
||
* some improvement
* some other exploration for the model
||
*
|-

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

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

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* Renew the project website and upload relevant speech sequences
* Draw various loss curves
* Prepare test data for content-relevant tests
||
* Quantitave test
* Prepare test data for speaker separation tests
||
*
|-

|-
|Zixi Yan
||
* Modify wav2vec-u gan network code and output intermediate results
* Training wav2vec2 model
||
*
||
*
|-

|-
|Sirui Li
||
* Compare the training process of TIMIT and Tibetan
||
* Fine-tune the Tibetan wav2vec model
* Prepare the thesis opening report
||
*
|-

|-
|Haoyu Jiang
||
*
||
*
||
*
|-

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

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

|}

2021-11-01

2021-11-01T01:35:06Z

Liangwd：

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

|-
|Yunqi Cai
||
* THS dataset experiments and paper
||
*
||
*
|-

|-
|Lantian Li
||
* Submit CNC response
* Complete project deliveries
||
* Hard trials
||
*
|-

|-
|Ying Shi
||
* Continue on KWS
||
*
||
*
|-

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

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

|-
|Pengqi Li
||
* egs of thc30 base sunine
* reproduce bubble noise on speech recognition
||
* audio important maps based bubble noise on speaker recognition
||
*
|-

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* several models tested including model without cycle loss, models with different bottleneck
||
* finetune these models decoders
||
*
|-

|-
|Zixi Yan
||
* analyse reason of the problem of wav2vec-u in Tibetan
||
*
||
*
|-

|-
|Sirui Li
||
* Gan network training code
* Mongolian recording project
||
* Adjust Tibetan wav2vec-u parameters
||
*
|-

|-
|Haoyu Jiang
||
* Voxceleb2 and Voxceleb1 data set collation
||
* single mode sota system training
||
*
|-

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

|}

2021-10-25

2021-10-25T01:32:10Z

Liangwd：

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

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

|-
|Lantian Li
||
* CNC response
* Project delivery
||
* Hard trials paper
||
*
|-

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

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

|-
|Tiankai Zhi
||
*
||
*
||
*
|-

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

|-
|Jingxin Shen
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
* audio important maps based mask
||
*
|-

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* Publish the baseline test data on the website
* Realize the cycle-loss model
||
* More models with different layers and parameters need to be tested
* Test whether the current model is better than baseline
||
*
|-

|}

2021-09-06

2021-09-06T05:33:44Z

Liangwd：

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

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

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

|-
|Ying Shi
||
* KWS
||
* Prepear ICASSP 2022
||
*
|-

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

|-
|Jiao Han
||
*
||
*
||
*
|-

|-
|Di Wang
||
*
||
*
||
*
|-

|-
|Tiankai Zhi
||
*
||
*
||
*
|-

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

|-
|Jingxin Shen
||
* Thermal face experiment with DNF
||
*
||
*
|-

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

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* Approach two accomplished
||
* Collect data and Build the project website
||
*
|-

|}

2021-08-30

2021-08-30T06:07:29Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Neural PCA experiments on FashionMNIST and kMNIST, [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=wangd&step=view_request&cvssid=830 link]
* Some variants of NPCA, in terms of sampling scheme, loss function, etc.
* Some work for thermal paper review
||
* TASLP paper response
* Continue the NPCA and paper review.
||
*
|-

|-
|Yunqi Cai
||
* TASLP paper experiments and response
* Thermal Speaking project
||
*
||
*
|-

|-
|Lantian Li
||
* Prepare multi-modal datasets of CN-Celeb.
* Monitor cvss 808 and 831.
||
* Paper of `Hard trials'
||
*
|-

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

|-
|Haoran Sun
||
* emotion recognition on MSP-IMPROV
||
* subjective evaluation
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|-
|Di Wang
||
* Complete cross-channel experiment doc.
||
* Data processing for CNC1 and CNC2.
||
*
|-

|-
|Tiankai Zhi
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* read paper about SN-net(two branchs DAE)
* attend graduate freshman lectures
||
* run UASR code
* attend graduate freshman lectures
||
*
|-

|-
|Jingxin Shen
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Compare MAML and R-MAML on MiniImagenet for Fast Adaptation
||
* study of [808]
||
*
|-

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* Try a two-step training to improve the baseline exemplar encoder
* Collect test data of the method
||
* Continue another possible method on multi-step training.
||
*
|-

|}

2021-08-30

2021-08-30T06:06:27Z

Liangwd：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-
|-
|Dong Wang
||
* Neural PCA experiments on FashionMNIST and kMNIST, [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=wangd&step=view_request&cvssid=830 link]
* Some variants of NPCA, in terms of sampling scheme, loss function, etc.
* Some work for thermal paper review
||
* TASLP paper response
* Continue the NPCA and paper review.
||
*
|-

|-
|Yunqi Cai
||
* TASLP paper experiments and response
* Thermal Speaking project
||
*
||
*
|-

|-
|Lantian Li
||
* Prepare multi-modal datasets of CN-Celeb.
* Monitor cvss 808 and 831.
||
* Paper of `Hard trials'
||
*
|-

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

|-
|Haoran Sun
||
* emotion recognition on MSP-IMPROV
||
* subjective evaluation
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|-
|Di Wang
||
* Complete cross-channel experiment doc.
||
* Data processing for CNC1 and CNC2.
||
*
|-

|-
|Tiankai Zhi
||
*
||
*
||
*
|-

|-
|Chen Chen
||
* read paper about SN-net(two branchs DAE)
* attend graduate freshman lectures
||
* run UASR code
* attend graduate freshman lectures
||
*
|-

|-
|Jingxin Shen
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Compare MAML and R-MAML on MiniImagenet for Fast Adaptation
||
* study of [808]
||
*
|-

|-
|Qingyang Zhu
||
*
||
*
||
*
|-

|-
|Weida Liang
||
* Try a two-step training to improve the baseline exemplar encoder
* Collect test data of the method
* Continue another possible method.
||
*
||
*
|-

|}

Weekly reading

2021-08-13T12:56:29Z

Liangwd：

'''清华大学语音语言中心内部学习会

'''时间：每周四晚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 || ||
|-
| 2021/08/26 ||Jingxin Shen || ||
|-
| 2021/09/02 ||Tiankai Zhi || ||
|-
| 2021/09/09 ||Jiao Han || ||
|-
| 2021/09/16 ||Haoran Sun || ||
|-
|}

[[Old readings|Past Events]]

Weekly reading

2021-08-13T12:55:30Z

Liangwd：

'''清华大学语音语言中心内部学习会

'''时间：每周四晚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 || ||
|-
| 2021/08/26 ||Jingxin Shen || ||
|-
| 2021/09/02 ||Tiankai Zhi || ||
|-
| 2021/09/09 ||Jiao Han || ||
|-
| 2021/09/16 ||Haoran Sun || ||
|-
|}

[[Old readings|Past Events]]

Weekly reading

2021-08-13T12:53:56Z

Liangwd：

'''清华大学语音语言中心内部学习会

'''时间：每周四晚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 AUDIOVISUAL SYNTHESIS VIA EXEMPLAR AUTOENCODERS ||
|-
| 2021/08/19 ||Di Wang || ||
|-
| 2021/08/26 ||Jingxin Shen || ||
|-
| 2021/09/02 ||Tiankai Zhi || ||
|-
| 2021/09/09 ||Jiao Han || ||
|-
| 2021/09/16 ||Haoran Sun || ||
|-
|}

[[Old readings|Past Events]]

文件:UNSUPERVISED AUDIOVISUAL SYNTHESIS VIA EXEMPLAR AUTOENCODERS.pdf

2021-08-13T06:51:30Z

Liangwd：