“2025-06-23”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（12位用户的12个中间修订版本未显示）
第6行： 第6行：
 
|Dong Wang
 
|Dong Wang
 
||
 
||
−
*  
+
* Primary School Version (3-6) draft done.
 +
* Travel to Xi'an
  
 
||
 
||
第43行： 第44行：
 
|Zhenghai You
 
|Zhenghai You
 
||
 
||
−
*  
+
* Paper reading & Weekly report
 
||
 
||
 
*
 
*
第65行： 第66行：
 
|Xiaolou Li
 
|Xiaolou Li
 
||
 
||
−
*  
+
* CNVSRC2025 VSR baseline training
 +
* CNVSRC2025 data preparation
 
||
 
||
 
*  
 
*  
第76行： 第78行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
*CNVSRC2025 VTS part Baseline code rewriting and checking （Finish）and uploading to github
 
||
 
||
 
*
 
*
第100行： 第102行：
 
|Wan Lin
 
|Wan Lin
 
||
 
||
−
*  
+
* supply experiments for ns paper
 
||
 
||
 
*
 
*
第111行： 第113行：
 
|Tianhao Wang
 
|Tianhao Wang
 
||
 
||
−
*  
+
* Huawei project things
 +
* huawei competition baseline data preparing
 
||
 
||
 
*
 
*
第122行： 第125行：
 
|Xiaoxue Luo
 
|Xiaoxue Luo
 
||
 
||
−
*  
+
* some test and data filtering of Huawei project
 +
* Write code for the new architecture of sound separation model(in progress)
 
||
 
||
 
*
 
*
第134行： 第138行：
 
||
 
||
 
* Hainan D&B Course teaching assistant
 
* Hainan D&B Course teaching assistant
−
* Do some ML book works
+
* Help do some ML book things
 
* Read paper
 
* Read paper
 
||
 
||
第150行： 第154行：
 
** Bussiness Plan completed
 
** Bussiness Plan completed
 
* ASR training
 
* ASR training
−
** remix max 8k and 16k data
+
** remix max 8k and 16k data, can train model after final check
−
** train asr model with decoder(try kl loss and cross entropy loss):LER higher than expectation
+
 
||
 
||
 
*
 
*
第162行： 第165行：
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
−
*  
+
* Hainan D&B Course teaching assistant
 +
* AED Quant bug fix (model preparing related)
 +
* Refine Technical Analysis policy for multi agent investment
 
||
 
||
 
*
 
*
第173行： 第178行：
 
|Wenqiang Du
 
|Wenqiang Du
 
||
 
||
−
*  
+
*Check and record AI courses from Jiaoyubu (4/12)
 
||
 
||
 
*
 
*
第184行： 第189行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*  
+
* Did experiment about mispronunciation detection about unclear pronunciation. Adaptation experiment is in progress.
 
||
 
||
 
*
 
*
第212行： 第217行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* (Continuous) integrating PJSIP to ESP32-based application.
 +
* Extended analysis based on on-device test results of Text-Enroll KWS + FunASR.
 
||
 
||
 
*
 
*

2025年6月23日 (一) 10:58的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Primary School Version (3-6) draft done.
  • Travel to Xi'an
Lantian Li
  • Write ML book (38/326)
  • Go on Hainan D&B Course
  • BUPT Graduate matters
Ying Shi
  • Write introduction of my thesis
Zhenghai You
  • Paper reading & Weekly report
Junming Yuan
  • Optimize ASR code(MT-HuBERT WER: 11.33%->7.39%)
  • JiaoYuBu AI lesson
Xiaolou Li
  • CNVSRC2025 VSR baseline training
  • CNVSRC2025 data preparation
Zehua Liu
  • CNVSRC2025 VTS part Baseline code rewriting and checking （Finish）and uploading to github
Pengqi Li
  • XAI paper-writing the draft.
  • JiaoYuBu AI lessons
  • TsingHua middle school AI class summer school prepare(Sunday)
Wan Lin
  • supply experiments for ns paper
Tianhao Wang
  • Huawei project things
  • huawei competition baseline data preparing
Xiaoxue Luo
  • some test and data filtering of Huawei project
  • Write code for the new architecture of sound separation model(in progress)
Junhui Chen
  • Hainan D&B Course teaching assistant
  • Help do some ML book things
  • Read paper
Jiaying Wang
  • GuoChuang competition：
    • Slides template modification
    • Bussiness Plan completed
  • ASR training
    • remix max 8k and 16k data, can train model after final check
Yu Zhang
  • Hainan D&B Course teaching assistant
  • AED Quant bug fix (model preparing related)
  • Refine Technical Analysis policy for multi agent investment
Wenqiang Du
  • Check and record AI courses from Jiaoyubu (4/12)
Yang Wei
  • Did experiment about mispronunciation detection about unclear pronunciation. Adaptation experiment is in progress.
Turi
Yue Gu
  • supplement a baseline and some alation experiments
  • revise my paper
Qi Qu
  • (Continuous) integrating PJSIP to ESP32-based application.
  • Extended analysis based on on-device test results of Text-Enroll KWS + FunASR.
取自“http://index.cslt.org/mediawiki/index.php?title=2025-06-23&oldid=43234”