“2025-05-19”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（15位用户的18个中间修订版本未显示）
第6行： 第6行：
 
|Dong Wang
 
|Dong Wang
 
||
 
||
−
*  
+
* Training for Tsinghua Primary School
 +
* Training for ZhongLv group
 +
* Refine AIGE book for college students
  
 
||
 
||
第18行： 第20行：
 
|Lantian Li
 
|Lantian Li
 
||
 
||
−
*  
+
* Huawei DiTing 3.0 delivery
 +
* BUPT Graduate matters
 
||
 
||
 
*
 
*
第41行： 第44行：
 
|Zhenghai You
 
|Zhenghai You
 
||
 
||
−
*  
+
* Some tests of Huawei project(emotion & targetless)
 +
* Revised Huawei report
 
||
 
||
 
*
 
*
第63行： 第67行：
 
|Xiaolou Li
 
|Xiaolou Li
 
||
 
||
−
*  
+
* Audit video data
 +
* Improve the speed of inference
 +
* Paper reading
 
||
 
||
 
*  
 
*  
第74行： 第80行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
* Audio video data check
 +
* help xiaolou to transfer web code to GA server
 +
* Paper reading
 
||
 
||
 
*
 
*
第85行： 第93行：
 
|Pengqi Li
 
|Pengqi Li
 
||
 
||
−
*  
+
* Organize a pre-experiment to explore the following questions:
 +
** How to evaluate reliability(some experiment shows reliability)
 +
** How to visualize (but still thinking about how to display the "explanation").
 
||
 
||
 
*
 
*
第96行： 第106行：
 
|Wan Lin
 
|Wan Lin
 
||
 
||
−
*  
+
* multi-scale feature exp: no improvement
 +
* reading paper
 
||
 
||
 
*
 
*
第107行： 第118行：
 
|Tianhao Wang
 
|Tianhao Wang
 
||
 
||
−
*  
+
* prepare huawei project meeting (history issues)
 +
* investigating some generative based separation model
 
||
 
||
 
*
 
*
第118行： 第130行：
 
|Xiaoxue Luo
 
|Xiaoxue Luo
 
||
 
||
−
*  
+
* Use some metrics in audio generation task to evaluate the performance of CLAPSep and our model
 
||
 
||
 
*
 
*
第140行： 第152行：
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
−
*
+
* reading paper
 +
* weekly report
 
||
 
||
−
*
+
*  
 
||
 
||
 
*
 
*
第151行： 第164行：
 
|Jiaying Wang
 
|Jiaying Wang
 
||
 
||
−
*
+
* ASR training
 +
** clean data ctc loss converge at 200 (higher than expactation)
 +
** LER have abnormal result：predicted labels tend to concentrate on a few letters, debuging
 +
* Modify the PPT for the hongyan campus competition.
 
||
 
||
 
*
 
*
第162行： 第178行：
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
−
*  
+
* For news and sentiment analysis, use reflection as "condition" instead of as "reference" [https://z1et6d3xtb.feishu.cn/docx/SZL2d3y3RolnXlxF02fcK03Bnqd?from=from_copylink]
 +
* Increase news sources (the abuse of reflection is often found when there is a lack of useful news on that day)
 +
* Adding more benchmark (implementing rule based benchmark in TradingAgents (MACD RSI ... ))
 
||
 
||
−
*
+
* Detail Analysis of current backtesting result and check the paper plan with Teacher Li
−
||
+
−
*
+
−
|-
+
−
 
+
  
 
|-
 
|-
 
|Wenqiang Du
 
|Wenqiang Du
 
||
 
||
−
*  
+
* Business trip to Changzhou
 
||
 
||
 
*
 
*
第184行： 第198行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*  
+
* Finish license check module for AIBabel ASR gRPC service.
 
||
 
||
 
*
 
*
第194行： 第208行：
 
|Turi
 
|Turi
 
||
 
||
−
*  
+
* Defense
 
||
 
||
 
*  
 
*  
第202行： 第216行：
 
|Yue Gu
 
|Yue Gu
 
||
 
||
−
*  
+
* fix a bug about a reproduced method and retrain the model
 +
* polish my introduction according to some suggestions
 
||
 
||
 
*
 
*
第211行： 第226行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* On-device text-enroll KWS demo.
 +
* Problem analysis: performance drop caused by precision loss in quantization. [https://b30lttjm7l.feishu.cn/docx/Vkjtd1cjboDD3Ex1xMGcq38WnQe?from=from_copylink]
 
||
 
||
 
*
 
*

2025年5月26日 (一) 10:33的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Training for Tsinghua Primary School
  • Training for ZhongLv group
  • Refine AIGE book for college students
Lantian Li
  • Huawei DiTing 3.0 delivery
  • BUPT Graduate matters
Ying Shi
Zhenghai You
  • Some tests of Huawei project(emotion & targetless)
  • Revised Huawei report
Junming Yuan
  • Extended ASR finetuning exp[1]
  • Review Middle-school AI practice handbook(9/20).
Xiaolou Li
  • Audit video data
  • Improve the speed of inference
  • Paper reading
Zehua Liu
  • Audio video data check
  • help xiaolou to transfer web code to GA server
  • Paper reading
Pengqi Li
  • Organize a pre-experiment to explore the following questions:
    • How to evaluate reliability(some experiment shows reliability)
    • How to visualize (but still thinking about how to display the "explanation").
Wan Lin
  • multi-scale feature exp: no improvement
  • reading paper
Tianhao Wang
  • prepare huawei project meeting (history issues)
  • investigating some generative based separation model
Xiaoxue Luo
  • Use some metrics in audio generation task to evaluate the performance of CLAPSep and our model
Zhenyu Zhou
Junhui Chen
  • reading paper
  • weekly report
Jiaying Wang
  • ASR training
    • clean data ctc loss converge at 200 (higher than expactation)
    • LER have abnormal result：predicted labels tend to concentrate on a few letters, debuging
  • Modify the PPT for the hongyan campus competition.
Yu Zhang
  • For news and sentiment analysis, use reflection as "condition" instead of as "reference" [2]
  • Increase news sources (the abuse of reflection is often found when there is a lack of useful news on that day)
  • Adding more benchmark (implementing rule based benchmark in TradingAgents (MACD RSI ... ))
  • Detail Analysis of current backtesting result and check the paper plan with Teacher Li
Wenqiang Du
  • Business trip to Changzhou
Yang Wei
  • Finish license check module for AIBabel ASR gRPC service.
Turi
  • Defense
Yue Gu
  • fix a bug about a reproduced method and retrain the model
  • polish my introduction according to some suggestions
Qi Qu
  • On-device text-enroll KWS demo.
  • Problem analysis: performance drop caused by precision loss in quantization. [3]
取自“http://index.cslt.org/mediawiki/index.php?title=2025-05-19&oldid=43139”