“2024-03-18”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第30行： 第30行：
 
* Finish INTERSPEECH paper
 
* Finish INTERSPEECH paper
 
* Investigate random order SOT for multi-talker ASR task
 
* Investigate random order SOT for multi-talker ASR task
−
** WER 26.2%
+
* 3-mix 0s offset test condition
 +
** DOM-SOT 20.51
 +
** PIT-SOT 23.26
 +
** random-order SOT 26.20
 
||
 
||
 
*  
 
*  

2024年3月18日 (一) 09:00的版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
Lantian Li
Ying Shi
  • Finish INTERSPEECH paper
  • Investigate random order SOT for multi-talker ASR task
  • 3-mix 0s offset test condition
    • DOM-SOT 20.51
    • PIT-SOT 23.26
    • random-order SOT 26.20
Zhenghai You
Junming Yuan
  • Make the plan for the large vocabulary pretraining task.
    • Focus on the experimental details of the few-shot paper from Google.
    • Try to address the 3 questions:
      • How to change MT pretraining model structure?
      • How to train three strictly comparable pretraining models based on MT, Hubert, and wav2vec?
      • Why does Hubert+MT perform significantly better?
Chen Chen
Xiaolou Li
Zehua Liu
Pengqi Li
Wan Lin
Tianhao Wang
Zhenyu Zhou
Junhui Chen
Jiaying Wang
Yu Zhang
Wenqiang Du
Yang Wei
Lily
取自“http://index.cslt.org/mediawiki/index.php?title=2024-03-18&oldid=41455”