“2025-04-28”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（6位用户的7个中间修订版本未显示）
第6行： 第6行：
 
|Dong Wang
 
|Dong Wang
 
||
 
||
−
*  
+
* Polish AI college version
 +
* Two talks in Guangxi
  
 
||
 
||
第78行： 第79行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
* Write GA doc (test report and mid term report)
 +
* Prepare the presentation PPT
 +
* Improve the VTS demo system
 
||
 
||
 
*
 
*
第159行： 第162行：
 
|Jiaying Wang
 
|Jiaying Wang
 
||
 
||
−
*
+
* finish linear ASR module training：ctc loss converge at around 60, test loss 115.4
 +
** testing letter error rate
 +
* Network+ presentation preparation with Qiang bro
 +
* weekly report
 
||
 
||
 
*
 
*
第192行： 第198行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*  
+
* Test backend ASR model with AIBabel keyword data.
 +
* Review the mispronunciation detection project.
 
||
 
||
 
*
 
*
第202行： 第209行：
 
|Turi
 
|Turi
 
||
 
||
−
*  
+
* Filled some thesis forms and paper reading
 
||
 
||
 
*  
 
*  
第210行： 第217行：
 
|Yue Gu
 
|Yue Gu
 
||
 
||
−
*  
+
* reproduce some exps about hotword
 +
* write the method part (30%)
 
||
 
||
 
*
 
*
第219行： 第227行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* Adding modules to codebase: converting models (text-enroll models, CED models and classifiers) to NPU format.
 +
* Some debugging on mr536 and v85se.
 
||
 
||
 
*
 
*

2025年4月29日 (二) 02:58的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Polish AI college version
  • Two talks in Guangxi
Lantian Li
  • CSTR report on TSE and USS.
  • Dissertation reviews
Ying Shi
  • thesis
Zhenghai You
  • Some tests of Huawei project
  • Writing the report of Huawei project
Junming Yuan
  • Make Jiaoyubu's AI lesson PPTs with Qiang bro
  • Add 3-mixed test results under 2-mix finetuning setting and revise CN version of MT-HuBERT paper
Xiaolou Li
  • Write GA doc (test report and mid term report)
  • Prepare the presentation PPT
  • Improve the VTS demo system
Zehua Liu
  • Write GA doc (test report and mid term report)
  • Prepare the presentation PPT
  • Improve the VTS demo system
Pengqi Li
  • Make Jiaoyubu's AI lesson PPTs with Qiang bro
  • Review my research.
Wan Lin
  • Finish model training, only some test tasks left
  • Write paper: finish intro, related, method
Tianhao Wang
  • Huawei huohua model training
  • demo
Xiaoxue Luo
  • compared CED topk labels with ground truth labels, most CED labels are parent labels of ground truth(eg.ground truth: Male speech,man speaking; CED label: Speech)
  • adjust the order of separating audio from low to high probability, it means that our method is effective(SDR: our method: 12.2182; reversed: 11.8793)
Zhenyu Zhou
Junhui Chen
  • Continue to write NS paper (soon discuss with LW)
Jiaying Wang
  • finish linear ASR module training：ctc loss converge at around 60, test loss 115.4
    • testing letter error rate
  • Network+ presentation preparation with Qiang bro
  • weekly report
Yu Zhang
  • add reflection and memory mechanism based on market feedback (still fine-tuning prompt)
  • try other policy fusion method, no significant improvement.
Wenqiang Du
  • Jiaoyubu's AI lesson（10/10）with Junming and Pengqi
  • Some tasks about company
Yang Wei
  • Test backend ASR model with AIBabel keyword data.
  • Review the mispronunciation detection project.
Turi
  • Filled some thesis forms and paper reading
Yue Gu
  • reproduce some exps about hotword
  • write the method part (30%)
Qi Qu
  • Adding modules to codebase: converting models (text-enroll models, CED models and classifiers) to NPU format.
  • Some debugging on mr536 and v85se.
取自“http://index.cslt.org/mediawiki/index.php?title=2025-04-28&oldid=43077”