“2024-09-02”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（14位用户的15个中间修订版本未显示）
第6行： 第6行：
 
|Dong Wang
 
|Dong Wang
 
||
 
||
−
*
+
* Middle School AI book v0.0
 
||
 
||
 
*
 
*
第17行： 第17行：
 
|Lantian Li
 
|Lantian Li
 
||
 
||
−
*
+
* GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh]
 +
* Apply for the AP title (Failed)
 +
* Submit two undergraduate thesis projects
 
||
 
||
 
*
 
*
第39行： 第41行：
 
|Zhenghai You
 
|Zhenghai You
 
||
 
||
−
*
+
* ICASSP exp and paper writing[https://z1et6d3xtb.feishu.cn/docx/MWO5dRL2FoGOpbx2IqRcDjgfnHh]
 
||
 
||
 
*
 
*
第51行： 第53行：
 
* mixed Hubert pretraining v1 (in progress)
 
* mixed Hubert pretraining v1 (in progress)
 
** still have some bugs
 
** still have some bugs
−
||
 
−
*
 
−
||
 
−
*
 
−
|-
 
−
 
−
 
−
|-
 
−
|Chen Chen
 
−
||
 
−
*
 
 
||
 
||
 
*
 
*
第83行： 第74行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
*CNVSRC 2024 Website Finish
 +
*ICASSP exp and paper writing[https://z1et6d3xtb.feishu.cn/docx/ZI2GdERFWoLGYNxDIfmcaPYxnwt?from=from_copylink]
 
||
 
||
 
*
 
*
第94行： 第86行：
 
|Pengqi Li
 
|Pengqi Li
 
||
 
||
−
*
+
* [https://z1et6d3xtb.feishu.cn/docx/ZsWRd4qi8ocZEwx6oPbcZG2unvc]Pondering the expected conclusions for paper
 +
* Experiment on timit(Finding and disadvantage)
 +
** poor consistency of TAO and LayerCAM methods
 +
** Toy Experiment
 +
* Challenge: Do the conclusions drawn from SID tasks (toy experiments) align with those from SV tasks (more SOTA models)?
 
||
 
||
−
*
+
* To investigate and reproduce existing interpretability methods for verification task.
 +
* To analyze the importance of phones using TTS datasets(broad coverage of phonemes) based SOTA models
 
||
 
||
 
*
 
*
第105行： 第102行：
 
|Wan Lin
 
|Wan Lin
 
||
 
||
−
*
+
* ICASSP paper writing
 
||
 
||
 
*
 
*
第127行： 第124行：
 
|Zhenyu Zhou
 
|Zhenyu Zhou
 
||
 
||
−
*
+
*check the conditional chain code
 
||
 
||
 
*
 
*
第138行： 第135行：
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
−
*
+
* Writing Neural Scoring paper, 1st ver. done.
 
||
 
||
 
*
 
*
第149行： 第146行：
 
|Jiaying Wang
 
|Jiaying Wang
 
||
 
||
−
*
+
* conditional chain code ready can run after double check
 
||
 
||
 
*
 
*
第160行： 第157行：
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
−
*
+
* reproduce iTransformer
 +
* Transfer iTrasnformer to financial data[https://z1et6d3xtb.feishu.cn/docx/ZwfLd73LZogGWFxtN6jcXAmxneh?from=from_copylink]
 
||
 
||
 
*
 
*
第171行： 第169行：
 
|Wenqiang Du
 
|Wenqiang Du
 
||
 
||
−
*
+
* Write middle school handbook(completed)
 +
* Continue  to training Chinese and Cantonese KWS model
 
||
 
||
 
*
 
*
第182行： 第181行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*
+
* Get familiar with text enroll KWS training
 
||
 
||
 
*
 
*
第192行： 第191行：
 
|Lily
 
|Lily
 
||
 
||
−
*
+
* AI-Radiance's daily work
 
||
 
||
 
*
 
*
第202行： 第201行：
 
|Turi
 
|Turi
 
||
 
||
−
*
+
* Working on dataset paper refinement & additional experiment
 +
** Attempting using pretrained model, not successful yet
 
||
 
||
 
*
 
*
第219行： 第219行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* KWS:
 +
** Cantonese train dataset collected and annotated: ~200 speakers, 10 keywords, 10 repeats per keyword.
 +
** More scene-specific test dataset collected: school, meeting, exhibition, etc.
 +
** Locating ideal keyword-wise thresholds for specific scenes using DCF (detection cost function).
 
||
 
||
 
*
 
*

2024年9月2日 (一) 10:55的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Middle School AI book v0.0
Lantian Li
  • GPU status [1]
  • Apply for the AP title (Failed)
  • Submit two undergraduate thesis projects
Ying Shi
Zhenghai You
  • ICASSP exp and paper writing[2]
Junming Yuan
  • mixed Hubert pretraining v1 (in progress)
    • still have some bugs
Xiaolou Li
Zehua Liu
  • CNVSRC 2024 Website Finish
  • ICASSP exp and paper writing[3]
Pengqi Li
  • [4]Pondering the expected conclusions for paper
  • Experiment on timit(Finding and disadvantage)
    • poor consistency of TAO and LayerCAM methods
    • Toy Experiment
  • Challenge: Do the conclusions drawn from SID tasks (toy experiments) align with those from SV tasks (more SOTA models)?
  • To investigate and reproduce existing interpretability methods for verification task.
  • To analyze the importance of phones using TTS datasets(broad coverage of phonemes) based SOTA models
Wan Lin
  • ICASSP paper writing
Tianhao Wang
Zhenyu Zhou
  • check the conditional chain code
Junhui Chen
  • Writing Neural Scoring paper, 1st ver. done.
Jiaying Wang
  • conditional chain code ready can run after double check
Yu Zhang
  • reproduce iTransformer
  • Transfer iTrasnformer to financial data[5]
Wenqiang Du
  • Write middle school handbook(completed)
  • Continue to training Chinese and Cantonese KWS model
Yang Wei
  • Get familiar with text enroll KWS training
Lily
  • AI-Radiance's daily work
Turi
  • Working on dataset paper refinement & additional experiment
    • Attempting using pretrained model, not successful yet
Yue Gu
Qi Qu
  • KWS:
    • Cantonese train dataset collected and annotated: ~200 speakers, 10 keywords, 10 repeats per keyword.
    • More scene-specific test dataset collected: school, meeting, exhibition, etc.
    • Locating ideal keyword-wise thresholds for specific scenes using DCF (detection cost function).
取自“http://cslt.org/mediawiki/index.php?title=2024-09-02&oldid=42198”