“2024-11-18”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（9位用户的12个中间修订版本未显示）
第18行： 第18行：
 
|Lantian Li
 
|Lantian Li
 
||
 
||
−
*
+
* AI-Graph EN Chapter 3 Done
 +
* 2025 Daily Sign v1.0 Done
 +
* CSTR Report
 
||
 
||
 
*
 
*
第29行： 第31行：
 
|Ying Shi
 
|Ying Shi
 
||
 
||
−
*  
+
* Test Google's product about sound separation
 +
* Correct the test results of the previous condition overlap asr model [https://z1et6d3xtb.feishu.cn/docx/GtmydP85Noq1eIx56z3c7qV5nWc?from=from_copylink here]
 
||
 
||
 
*
 
*
第75行： 第78行：
 
|Xiaolou Li
 
|Xiaolou Li
 
||
 
||
−
*
+
* Finally finish the VTS report
 +
* Data preparation
 +
** CVS3 process 1/4
 +
** take over webVideo from SUN CHANG and preprocess it through auto-avsr pipline
 +
* Code preparation
 +
** Finish the Conformer/CTC pretraining code
 +
** Still debuging AVHuBERT pretraining code
 +
* Paper reading...
 
||
 
||
 
*
 
*
第86行： 第96行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
*VTS Documents Revise with Xiaolou
 +
*Iterative inference training
 +
*LLM Different context length[https://z1et6d3xtb.feishu.cn/docx/JBsidACDVojhCaxFQLbcCVbsnAc?from=from_copylink]
 
||
 
||
 
*
 
*
第119行： 第131行：
 
|-
 
|-
 
|Tianhao Wang
 
|Tianhao Wang
 +
||
 +
* organizing the exp plan and modify the code for In-context-Audio-Retrieval (in training)
 
||
 
||
 
*
 
*
 +
||
 +
*
 +
|-
 +
 +
 +
|-
 +
|Xiaoxue Luo
 +
||
 +
* prepare the code for CED+AudioSep
 +
* participate in an AI competition with Wenqiang and Zhangyu
 
||
 
||
 
*
 
*
第131行： 第155行：
 
|Zhenyu Zhou
 
|Zhenyu Zhou
 
||
 
||
−
*
+
*Huawei project
 +
*read papers
 +
*code review(Design new ordering method)
 
||
 
||
 
*
 
*
第164行： 第190行：
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
−
*
+
* ICCIP 2024
 +
* Paper reading about LLM Market Simulation
 
||
 
||
 
*
 
*
第175行： 第202行：
 
|Wenqiang Du
 
|Wenqiang Du
 
||
 
||
−
*
+
* ICCIP2024
 +
* Participated in an AI competition
 +
 
 +
 
 
||
 
||
 
*
 
*
第186行： 第216行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*
+
* Do text enroll kws model experiment on small data set.(https://z1et6d3xtb.feishu.cn/docx/WLLLd2zQvoiE78xfMhpcHejdnnd)
 
||
 
||
 
*
 
*
第214行： 第244行：
 
|Yue Gu
 
|Yue Gu
 
||
 
||
−
* synthesis some audios for target speakers
+
* synthesis some audios for target speakers [https://j1kw9qcmaxp.feishu.cn/wiki/CZDTwKdPwi3mvTk9BJccdifZnEb?from=from_copylink]
 
* paper writing
 
* paper writing
 
||
 
||
第224行： 第254行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* Knock detection: output every knock's offset so that a shorter audio can be built to speed up human verification.
 +
* Text-enroll KWS: model i/o optimized; 2.5x faster than the first version.
 +
* KWS: Chongqing dialect train dataset (15 keywords, ~24.5k utterances).
 +
* Exp. using new FunASR model (SeACoParaformer) for cloud verification, which handles hotwords better.
 +
* Exp. using B0-based KWS model for local verification after detection from Chipintelli's chip.
 
||
 
||
 
*
 
*

2024年11月18日 (一) 11:14的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • 2nd round check for middle-school AI handbook
  • AI training for teachres of Tsinghua Middle School
Lantian Li
  • AI-Graph EN Chapter 3 Done
  • 2025 Daily Sign v1.0 Done
  • CSTR Report
Ying Shi
  • Test Google's product about sound separation
  • Correct the test results of the previous condition overlap asr model here
Zhenghai You
Junming Yuan
  • reproduce cocktail-Hubert
  • feat-mask MT-Hubert
    • change training strategy
  • result in [1]
Chen Chen
Xiaolou Li
  • Finally finish the VTS report
  • Data preparation
    • CVS3 process 1/4
    • take over webVideo from SUN CHANG and preprocess it through auto-avsr pipline
  • Code preparation
    • Finish the Conformer/CTC pretraining code
    • Still debuging AVHuBERT pretraining code
  • Paper reading...
Zehua Liu
  • VTS Documents Revise with Xiaolou
  • Iterative inference training
  • LLM Different context length[2]
Pengqi Li
  • Summarize recently work and report.
  • Mapping to IPA from diff language.
  • Write Paper.
Wan Lin
Tianhao Wang
  • organizing the exp plan and modify the code for In-context-Audio-Retrieval (in training)
Xiaoxue Luo
  • prepare the code for CED+AudioSep
  • participate in an AI competition with Wenqiang and Zhangyu
Zhenyu Zhou
  • Huawei project
  • read papers
  • code review(Design new ordering method)
Junhui Chen
Jiaying Wang
Yu Zhang
  • ICCIP 2024
  • Paper reading about LLM Market Simulation
Wenqiang Du
  • ICCIP2024
  • Participated in an AI competition


Yang Wei
Lily
Turi
Yue Gu
  • synthesis some audios for target speakers [3]
  • paper writing
Qi Qu
  • Knock detection: output every knock's offset so that a shorter audio can be built to speed up human verification.
  • Text-enroll KWS: model i/o optimized; 2.5x faster than the first version.
  • KWS: Chongqing dialect train dataset (15 keywords, ~24.5k utterances).
  • Exp. using new FunASR model (SeACoParaformer) for cloud verification, which handles hotwords better.
  • Exp. using B0-based KWS model for local verification after detection from Chipintelli's chip.
取自“http://index.cslt.org/mediawiki/index.php?title=2024-11-18&oldid=42461”