“2025-07-07”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（9位用户的10个中间修订版本未显示）
第42行： 第42行：
 
|Zhenghai You
 
|Zhenghai You
 
||
 
||
−
*  
+
* Reproduce the VAE of SoloSpeech
 
||
 
||
 
*
 
*
第52行： 第52行：
 
|Junming Yuan
 
|Junming Yuan
 
||
 
||
−
*  
+
* Middle-school AI Textbook
 +
* revise High-school slides
 
||
 
||
 
*
 
*
第74行： 第75行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
*CNVSRC2025 website design and release
 +
*Reading paper
 
||
 
||
 
*
 
*
第96行： 第98行：
 
|Wan Lin
 
|Wan Lin
 
||
 
||
−
*  
+
* Revised paper and submitted
 +
* Exp:
 +
** loaded and fixed 1-layer feature extractor for 8 layer: no improvement
 +
** run 1-layer NS with 1.5k enroll per test
 
||
 
||
 
*
 
*
第107行： 第112行：
 
|Tianhao Wang
 
|Tianhao Wang
 
||
 
||
−
*  
+
*re-run the experiments for my paper
 +
*paper reading about generative sound sep
 
||
 
||
 
*
 
*
第118行： 第124行：
 
|Xiaoxue Luo
 
|Xiaoxue Luo
 
||
 
||
−
*  
+
* trained the new architecture(base version) of sound separation, but the test results are not very good. It may be because there is too little training data after filtering, so I have added some data from vggsound, the model is in training.
 +
* some test of Huawei project
 
||
 
||
 
*
 
*
第129行： 第136行：
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
−
*
+
* Revise NS paper
 +
* Read nuclear power plant code
 +
* Read paper
 
||
 
||
 
*
 
*
第140行： 第149行：
 
|Jiaying Wang
 
|Jiaying Wang
 
||
 
||
−
*
+
* ASR training
 +
** Libri2Mix clean data：30epoch LER14.043%， 70epoch LER12.01%（align with shiying）
 +
** Use Libri2Mix noise data still training
 
||
 
||
 
*
 
*
第162行： 第173行：
 
|Wenqiang Du
 
|Wenqiang Du
 
||
 
||
−
*  
+
* Primary-school AI Textbook
 
||
 
||
 
*
 
*
第173行： 第184行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*  
+
* More attempts to improve mispronounce detection performance by adapting the AM (not work, F1 23% -> 18%)
 +
* Check primary school material
 
||
 
||
 
*
 
*
第200行： 第212行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* Some trivial development work.
 
||
 
||
 
*
 
*

2025年7月7日 (一) 12:35的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
Lantian Li
Ying Shi
  • thesis
  • some discussions with HUAWEI regarding the evaluation criteria of sound separation project.
Zhenghai You
  • Reproduce the VAE of SoloSpeech
Junming Yuan
  • Middle-school AI Textbook
  • revise High-school slides
Xiaolou Li
Zehua Liu
  • CNVSRC2025 website design and release
  • Reading paper
Pengqi Li
Wan Lin
  • Revised paper and submitted
  • Exp:
    • loaded and fixed 1-layer feature extractor for 8 layer: no improvement
    • run 1-layer NS with 1.5k enroll per test
Tianhao Wang
  • re-run the experiments for my paper
  • paper reading about generative sound sep
Xiaoxue Luo
  • trained the new architecture(base version) of sound separation, but the test results are not very good. It may be because there is too little training data after filtering, so I have added some data from vggsound, the model is in training.
  • some test of Huawei project
Junhui Chen
  • Revise NS paper
  • Read nuclear power plant code
  • Read paper
Jiaying Wang
  • ASR training
    • Libri2Mix clean data：30epoch LER14.043%， 70epoch LER12.01%（align with shiying）
    • Use Libri2Mix noise data still training
Yu Zhang
  • Label launch work for the acceptance of the RoyalFlush project (mainly SQL coding and HIVE pipeline)
Wenqiang Du
  • Primary-school AI Textbook
Yang Wei
  • More attempts to improve mispronounce detection performance by adapting the AM (not work, F1 23% -> 18%)
  • Check primary school material
Turi
Yue Gu
  • polish my journal paper and wirte the response
Qi Qu
  • Some trivial development work.
取自“http://index.cslt.org/mediawiki/index.php?title=2025-07-07&oldid=43268”