“2019-12-09”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“{| class="wikitable" !People !! This Week !! Next Week !! Task Tracking (<font color="red">DeadLine</font>) |- |- |Dong Wang || * || * || * |- |- |Yunqi Cai...”为内容创建页面)
 
 
(9位用户的11个中间修订版本未显示)
第6行: 第6行:
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
*  
+
* MelGan and WaveGlow re-investigation. Good neural vocoder is done.
 +
* Paper review on ICASSP 19, Interspeech 19.
 
||
 
||
*  
+
* Investigate the performance degradation with pure VP-based x-vector regularization compared to the VP+linear model
 +
* Design more concrete way of 'supervised flow', that involves supervision in sparse dimensions.
 +
* Paper review on NIPS 19.
 
||
 
||
 
*   
 
*   
第17行: 第20行:
 
|Yunqi Cai
 
|Yunqi Cai
 
||  
 
||  
*  
+
* VP-flow-lda Finished;
 
||
 
||
*  
+
* 1 try VP-flow without the last layer maping matrix
 +
* 2 control the class covariance matrix
 +
* 3 explore the fitting limit of VP-flow
 
||
 
||
 
*   
 
*   
第28行: 第33行:
 
|Zhiyuan Tang
 
|Zhiyuan Tang
 
||  
 
||  
*  
+
* WaveGlow model for audio augmentation.
 
||
 
||
*  
+
* Test whether the aug helps ASR/VPR.
 
||
 
||
 
*   
 
*   
第39行: 第44行:
 
|Lantian Li
 
|Lantian Li
 
||  
 
||  
*  
+
* Fix bugs in fnvpr, and release vpr product packages.
 +
* Pull request egs of CN-Celeb.
 +
* Study on flow models.
 
||
 
||
*  
+
* Hire-Flow
 
||
 
||
 
*   
 
*   
第50行: 第57行:
 
|Ying Shi
 
|Ying Shi
 
||  
 
||  
*  
+
* experiment about  flow denoise
 
||
 
||
*  
+
* finish the experiment and record it on cvss
 +
* write patent
 
||
 
||
 
*   
 
*   
第60行: 第68行:
 
|-
 
|-
 
|Wenqiang Du
 
|Wenqiang Du
 +
||
 +
* Model parameter adjustment about my graduation thesis
 +
||
 +
* End2end in my graduation thesis
 +
||
 +
 +
|-
 +
 +
 +
|-
 +
|Haoran Sun
 
||  
 
||  
 
*  
 
*  
第72行: 第91行:
 
|Yue Fan
 
|Yue Fan
 
||  
 
||  
*  
+
* experiments on flow
 
||
 
||
*  
+
* do the experiments and record it on cvss
 
||
 
||
 
*   
 
*   
第82行: 第101行:
 
|-
 
|-
 
|Jiawen Kang
 
|Jiawen Kang
 +
||
 +
* Sent materials to CUHK;
 +
* Reading paper about model robustness;
 +
* Kaldi egs checking.
 +
||
 +
* Experiences about CN-Celeb;
 +
* Preparing for CUHK inverview.
 +
||
 +
 +
|-
 +
 +
 +
|-
 +
|Ruiqi Liu
 +
||
 +
* Do experiments on CN-Celeb egs and VGG.
 +
* tf-kaldi
 +
||
 +
* Experiments according to last week's plan
 +
||
 +
 +
|-
 +
 +
 +
|-
 +
|Sitong Cheng
 
||  
 
||  
 
*  
 
*  
第92行: 第137行:
  
 
|-
 
|-
|Ruiqi Liu
+
|Zhixin Liu
 
||  
 
||  
 
*  
 
*  

2019年12月9日 (一) 00:43的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • MelGan and WaveGlow re-investigation. Good neural vocoder is done.
  • Paper review on ICASSP 19, Interspeech 19.
  • Investigate the performance degradation with pure VP-based x-vector regularization compared to the VP+linear model
  • Design more concrete way of 'supervised flow', that involves supervision in sparse dimensions.
  • Paper review on NIPS 19.
Yunqi Cai
  • VP-flow-lda Finished;
  • 1 try VP-flow without the last layer maping matrix
  • 2 control the class covariance matrix
  • 3 explore the fitting limit of VP-flow
Zhiyuan Tang
  • WaveGlow model for audio augmentation.
  • Test whether the aug helps ASR/VPR.
Lantian Li
  • Fix bugs in fnvpr, and release vpr product packages.
  • Pull request egs of CN-Celeb.
  • Study on flow models.
  • Hire-Flow
Ying Shi
  • experiment about flow denoise
  • finish the experiment and record it on cvss
  • write patent
Wenqiang Du
  • Model parameter adjustment about my graduation thesis
  • End2end in my graduation thesis
Haoran Sun
Yue Fan
  • experiments on flow
  • do the experiments and record it on cvss
Jiawen Kang
  • Sent materials to CUHK;
  • Reading paper about model robustness;
  • Kaldi egs checking.
  • Experiences about CN-Celeb;
  • Preparing for CUHK inverview.
Ruiqi Liu
  • Do experiments on CN-Celeb egs and VGG.
  • tf-kaldi
  • Experiments according to last week's plan
Sitong Cheng
Zhixin Liu