“2024-03-25”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（17位用户的24个中间修订版本未显示）
第6行： 第6行：
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
−
*  
+
* Design learn not to listen, to reduce false alarms for KWS [https://z1et6d3xtb.feishu.cn/wiki/UTS6w71hOio23ikNT2XcPvbznkd?fromShareWithMeNew=1]
 +
* Design AI courses for primary and middle schools
 +
* Finaly review of NeuralMag paper [https://www.overleaf.com/project/655f2c44824b8de1fdfeae23]
 +
* Rebutal for IJCAI paper [https://www.overleaf.com/project/65f96c74e1c7f322aea4477c]
 
||
 
||
 
*
 
*
第17行： 第20行：
 
|Lantian Li
 
|Lantian Li
 
||
 
||
−
*  
+
* GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh]
 +
* Rebutal for IJCAI paper
 +
* ASIP-BUPT (CohortTSE, NeuralScoring)
 
||
 
||
 
*  
 
*  
第23行： 第28行：
 
*   
 
*   
 
|-
 
|-
 +
  
  
第28行： 第34行：
 
|Ying Shi
 
|Ying Shi
 
||  
 
||  
−
*
+
* Experimental Result for SPL Paper: Phrase Guided End-to-End Target Sentence Extraction from Overlapping Speech
 +
* Data Preparation
 +
** Chinese Overlap ASR model
 +
** Detect wake-up words from  Continuous speech
 
||
 
||
−
*  
+
* Finish  draft for SPL paper 
 +
* Finish model training
 
||
 
||
 
*   
 
*   
第39行： 第49行：
 
|Zhenghai You
 
|Zhenghai You
 
||  
 
||  
−
*  
+
* A matching encoder experiment in cohort[https://z1et6d3xtb.feishu.cn/wiki/SOROw3itGi2Ql1k25bhcqdonnfb]
 
||
 
||
 
*  
 
*  
第49行： 第59行：
 
|Junming Yuan
 
|Junming Yuan
 
||  
 
||  
−
*
+
* Experimental report on "learn not to listen"[https://z1et6d3xtb.feishu.cn/docx/W6j4dOZ6WoFU9Lx0BLfc7QR6npd]
 
||
 
||
 
*
 
*
第60行： 第70行：
 
|Chen Chen
 
|Chen Chen
 
||  
 
||  
−
*  
+
* entropy analysis
 +
* group work [https://z1et6d3xtb.feishu.cn/docx/J1iydOXe3owSpgxwwxucHFIxnXd?from=from_copylink]
 
||
 
||
−
*  
+
* thesis
 
||
 
||
 
*   
 
*   
第71行： 第82行：
 
|Xiaolou Li
 
|Xiaolou Li
 
||  
 
||  
−
*  
+
* Reproduce different structure
 +
** Baseline training with less data
 +
** Code write and debug
 +
*** ResNet3D, Branchformer, E-Branchformer, interCTC
 +
* Paper Reading: Some VSR paper in ICASSP2024
 
||
 
||
−
*  
+
* Experiment in different structure
 
||
 
||
 
*   
 
*   
第82行： 第97行：
 
|Zehua Liu
 
|Zehua Liu
 
||  
 
||  
−
*
+
* ASR training for model distillation
 +
* Paper Reading
 
||
 
||
 
*  
 
*  
第93行： 第109行：
 
|Pengqi Li
 
|Pengqi Li
 
||   
 
||   
 +
* summary[https://z1et6d3xtb.feishu.cn/sheets/TISnsS8omhWfOstgoxocGNOFnrd] of speech processing XAI for NSFC
 +
** download 160+ papers(113 about speech processing XAI; Traditional XAI method; review)
 +
** Summarize them using LLM and categorize by speech processing task.
 +
||
 
*  
 
*  
 
||
 
||
−
*
+
* 3.28 will finish v1
−
||
+
−
* 
+
 
|-
 
|-
  
第104行： 第122行：
 
|Wan Lin
 
|Wan Lin
 
||  
 
||  
−
*  
+
* Neural scoring [https://z1et6d3xtb.feishu.cn/docx/TQvWdk8LVo9ONaxQ5Qac9A2Dn3d?from=from_copylink]
 
||
 
||
 
*
 
*
第115行： 第133行：
 
|Tianhao Wang
 
|Tianhao Wang
 
||  
 
||  
−
*  
+
* Neural scoring docs and codes reviewing
 
||
 
||
 
*  
 
*  
第126行： 第144行：
 
|Zhenyu Zhou
 
|Zhenyu Zhou
 
||  
 
||  
−
*
+
* Neural scoring docs and codes reviewing
 
||
 
||
 
*
 
*
第137行： 第155行：
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
−
*  
+
* Neural scoring: mix/overlap/concat test
 
||
 
||
 
*
 
*
第148行： 第166行：
 
|Jiaying Wang
 
|Jiaying Wang
 
||  
 
||  
−
*  
+
* one cohort distance test(The probability of selecting the source closer to the cohort as the target during testing)
 +
** the rate is still around 0.5
 +
* speakerbeam with no enroll/cohort + minimal loss training
 +
** double-check done
 +
** still training, but seem to converge at val_loss around -3
 +
** confused
 
||
 
||
 
*  
 
*  
第159行： 第182行：
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
−
*  
+
* Financial Backtest indicators check
 +
* Jun Wang R2 SAC codes and papers reading
 
||
 
||
−
*
+
* Reproduce R2 SAC and FinRL policy
 
||
 
||
 
*   
 
*   
第170行： 第194行：
 
|Wenqiang Du
 
|Wenqiang Du
 
||  
 
||  
−
* update CN KWS model
+
* update CN KWS model for AIbabel
 
**  Using real environment and FA data to update the model
 
**  Using real environment and FA data to update the model
 
||
 
||
第182行： 第206行：
 
|Yang Wei
 
|Yang Wei
 
||  
 
||  
−
*  
+
* Prepare for children mispronunciation detection and diagnosis base model
 
||
 
||
 
*
 
*
第192行： 第216行：
 
|Lily
 
|Lily
 
||
 
||
−
*  
+
* Paper reading and prepare for journal paper
 +
* Data annotation (for perception)
 +
||
 +
*
 +
||
 +
* 
 +
|-
 +
 
 +
|-
 +
|Turi
 +
||
 +
* Data Collection App Backend [https://uestc.feishu.cn/docx/RIlNdbYMYovoMXxl98OcouP6nsb?from=from_copylink]
 +
** User authentication
 +
** Data storage
 
||
 
||
 
*
 
*

2024年4月1日 (一) 03:47的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Design learn not to listen, to reduce false alarms for KWS [1]
  • Design AI courses for primary and middle schools
  • Finaly review of NeuralMag paper [2]
  • Rebutal for IJCAI paper [3]
Lantian Li
  • GPU status [4]
  • Rebutal for IJCAI paper
  • ASIP-BUPT (CohortTSE, NeuralScoring)
Ying Shi
  • Experimental Result for SPL Paper: Phrase Guided End-to-End Target Sentence Extraction from Overlapping Speech
  • Data Preparation
    • Chinese Overlap ASR model
    • Detect wake-up words from Continuous speech
  • Finish draft for SPL paper
  • Finish model training
Zhenghai You
  • A matching encoder experiment in cohort[5]
Junming Yuan
  • Experimental report on "learn not to listen"[6]
Chen Chen
  • entropy analysis
  • group work [7]
  • thesis
Xiaolou Li
  • Reproduce different structure
    • Baseline training with less data
    • Code write and debug
      • ResNet3D, Branchformer, E-Branchformer, interCTC
  • Paper Reading: Some VSR paper in ICASSP2024
  • Experiment in different structure
Zehua Liu
  • ASR training for model distillation
  • Paper Reading
Pengqi Li
  • summary[8] of speech processing XAI for NSFC
    • download 160+ papers(113 about speech processing XAI; Traditional XAI method; review)
    • Summarize them using LLM and categorize by speech processing task.
  • 3.28 will finish v1
Wan Lin
  • Neural scoring [9]
Tianhao Wang
  • Neural scoring docs and codes reviewing
Zhenyu Zhou
  • Neural scoring docs and codes reviewing
Junhui Chen
  • Neural scoring: mix/overlap/concat test
Jiaying Wang
  • one cohort distance test(The probability of selecting the source closer to the cohort as the target during testing)
    • the rate is still around 0.5
  • speakerbeam with no enroll/cohort + minimal loss training
    • double-check done
    • still training, but seem to converge at val_loss around -3
    • confused
Yu Zhang
  • Financial Backtest indicators check
  • Jun Wang R2 SAC codes and papers reading
  • Reproduce R2 SAC and FinRL policy
Wenqiang Du
  • update CN KWS model for AIbabel
    • Using real environment and FA data to update the model
Yang Wei
  • Prepare for children mispronunciation detection and diagnosis base model
Lily
  • Paper reading and prepare for journal paper
  • Data annotation (for perception)
Turi
  • Data Collection App Backend [10]
    • User authentication
    • Data storage
取自“http://index.cslt.org/mediawiki/index.php?title=2024-03-25&oldid=41517”