“2019-12-09”版本间的差异
来自cslt Wiki
| （9位用户的10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61行： | 第69行： | ||
|Wenqiang Du | |Wenqiang Du | ||
|| | || | ||
| − | * | + | * Model parameter adjustment about my graduation thesis |
|| | || | ||
| − | * | + | * End2end in my graduation thesis |
|| | || | ||
* | * | ||
| 第83行： | 第91行： | ||
|Yue Fan | |Yue Fan | ||
|| | || | ||
| − | * | + | * experiments on flow |
|| | || | ||
| − | * | + | * do the experiments and record it on cvss |
|| | || | ||
* | * | ||
| 第94行： | 第102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. | ||
|| | || | ||
* | * | ||
| 第105行： | 第116行： | ||
|Ruiqi Liu | |Ruiqi Liu | ||
|| | || | ||
| − | * | + | * Do experiments on CN-Celeb egs and VGG. |
| + | * tf-kaldi | ||
|| | || | ||
| − | * | + | * Experiments according to last week's plan |
|| | || | ||
* | * | ||
2019年12月9日 (一) 00:43的最后版本
| People | This Week | Next Week | Task Tracking (DeadLine) |
|---|---|---|---|
| Dong Wang |
|
|
|
| Yunqi Cai |
|
|
|
| Zhiyuan Tang |
|
|
|
| Lantian Li |
|
|
|
| Ying Shi |
|
|
|
| Wenqiang Du |
|
|
|
| Haoran Sun |
|
|
|
| Yue Fan |
|
|
|
| Jiawen Kang |
|
|
|
| Ruiqi Liu |
|
|
|
| Sitong Cheng |
|
|
|
| Zhixin Liu |
|
|
|
