“2024-11-25”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第91行： 第91行：
 
||
 
||
 
*Rebutall writing
 
*Rebutall writing
−
*Iterative training
+
*Iterative training and inference
 
**Iter-1(45.53%) < Iter-2(45.00%) < Iter-3(44.85%)  
 
**Iter-1(45.53%) < Iter-2(45.00%) < Iter-3(44.85%)  
 
||
 
||
第138行： 第138行：
 
|Zhenyu Zhou
 
|Zhenyu Zhou
 
||
 
||
−
*
+
*Speaker identity based conditional chain proposal[https://z1et6d3xtb.feishu.cn/docx/MzZ8d3cDWokCzCx0MmDcRJDFnke]
 +
*prepare Interim Report
 +
 
 
||
 
||
 
*
 
*

2024年11月25日 (一) 10:47的版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • 2nd round of check for AI handbook middle school.
  • Deal with pictures in AI handbook (primary & middle).
  • Start to check AI handbook high school.
  • Check AI book for Tianjin medical school.
Lantian Li
  • Complete my CSTR Report
  • Go on AI-Graph EN Chapter 4
  • Polish 2025 Daily Sign
Ying Shi
  • Design cohort- conditional chain mutli-talker ASR with round-RNN
  • WER result : round-1 32.15% , round-2: 69.69 round-3: 92.33%
  • For 500 utterances sub-test set: Only 28% of the sentences have a recognition order that matches the cosine distance.
Zhenghai You
  • Huawei TSE(Train models that better fit the scene)
Junming Yuan
  • Comparable results between Clean-HuBERT, Cocktail-HuBERT, and MT-HuBERT[1]
    • Bad news: Cocktail-HuBERT > Clean-HuBERT > MT-HuBERT
Chen Chen
Xiaolou Li
Zehua Liu
  • Rebutall writing
  • Iterative training and inference
    • Iter-1(45.53%) < Iter-2(45.00%) < Iter-3(44.85%)
Pengqi Li
  • Begin writing paper about importance of phonemes analysis work.
  • Reading a doctoral thesis on speaker explainability[2].
Wan Lin
Tianhao Wang
Zhenyu Zhou
  • Speaker identity based conditional chain proposal[3]
  • prepare Interim Report
Junhui Chen
Jiaying Wang
Yu Zhang
  • Huawei AED
    • data aug & human annotated dataset [4]
  • Finance
    • Paper reading, reproduce local Llama version of StockAgent [5] (a LLM based market simulation framework)
Wenqiang Du
  • Training of New language Models(HeNan)[6]
  • Training of New language Models(ChongQing)[7]
Yang Wei
Lily
Turi
  • Paper reading
  • ICASSP 2025 rebuttal
Yue Gu
Qi Qu
  • Finding ideal thresholds and deploying cloud services for KWS models: `zh48_guangdong` and `zh48_haining20`.
  • Located and fixed a bug in FunASR which may lead to segmentation fault. Built service with extended gRPC protocol.
  • Analysis of some AED (cries and slaps) FAs.
取自“http://cslt.org/mediawiki/index.php?title=2024-11-25&oldid=42542”