“2022-03-14”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(9位用户的12个中间修订版本未显示)
第5行: 第5行:
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
*
+
* Keep on revising the TASLP paper
 +
* More review on disentanglement
 
||
 
||
*
+
* Finish review disentanglement
 
||
 
||
 
*   
 
*   
第16行: 第17行:
 
|Yunqi Cai
 
|Yunqi Cai
 
||   
 
||   
*
+
* revise and submit NSFC project
 
||
 
||
 
*  
 
*  
第27行: 第28行:
 
|Lantian Li
 
|Lantian Li
 
||  
 
||  
*  
+
* Push CNCSRC (Submission system, Leaderboard and Evaluation toolkit)
 +
* PUFA project delivery
 
||
 
||
*  
+
* Release CNCSRC Submission and Leaderboard
 +
* PUFA project delivery
 
||
 
||
 
*   
 
*   
第38行: 第41行:
 
|Ying Shi
 
|Ying Shi
 
||  
 
||  
* The WAV2VEC model trained by Librispeech dataset was used for Chinese Asr experiments
+
* 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
 
||
 
||
 
*   
 
*   
第72行: 第76行:
 
|Pengqi Li
 
|Pengqi Li
 
||   
 
||   
*  
+
* do more experiments on visualization
 
||
 
||
 
*  
 
*  
第83行: 第87行:
 
|Weida Liang
 
|Weida Liang
 
||   
 
||   
*
+
* various tests with GOP SCA MOSNet and CER scoring
 +
* 4 Spk VC done
 +
* modify paper
 
||
 
||
*
+
* try 6 Spk VC
 +
* submit paper
 
||
 
||
 
*   
 
*   
第93行: 第100行:
 
|Zixi Yan
 
|Zixi Yan
 
||   
 
||   
*
+
* The WAV2VEC model trained by Librispeech dataset was used for Chinese Asr experiments
 
||
 
||
 
*
 
*
第103行: 第110行:
 
|Sirui Li
 
|Sirui Li
 
||   
 
||   
* Phoneme set discovery and dictionary generation
+
* Phoneme set discovery and dictionary generation [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/ed/Thchs30_moses_lexicon.pdf pdf]
 
||
 
||
*
+
* Improve phoneme translation system
 
||
 
||
 
*   
 
*   
第114行: 第121行:
 
|Haoyu Jiang
 
|Haoyu Jiang
 
||  
 
||  
*
+
* Data statistics of AV-CN-Celeb
 
||
 
||
*
+
* Design SOTA model test experiment
 
||
 
||
 
*   
 
*   

2022年3月14日 (一) 11:20的最后版本

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 here
  • Continue work on speech engrave: Design more smart mask mechanisms
Haoran Sun
  • results of CycleVC 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 pdf
  • 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