“2024-08-05”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(16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
 
||
 
||
*
+
* AC-SQL paper for KDD
 +
* Several public talks
 +
* Review for ISCSLP
 +
 
 
||
 
||
 
*
 
*
第17行: 第20行:
 
|Lantian Li
 
|Lantian Li
 
||
 
||
*
+
* GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh]
 +
* AI graph
 +
** QA slides checked
 
||
 
||
*
+
* High school handbook (20/40)
 
||
 
||
*
+
*  
 
|-
 
|-
  
第38行: 第43行:
 
|-
 
|-
 
|Zhenghai You
 
|Zhenghai You
||
+
||  
*
+
* Fix mutil-scale loss bug in Ex-former(u-net)
 +
* Tse Project: The performance of the pre-trained model on 12 spk data is poor
 +
* Writing ICCIP2024 & Complete the experiment
 
||
 
||
 
*
 
*
第49行: 第56行:
 
|Junming Yuan
 
|Junming Yuan
 
||
 
||
*
+
* Hubert pretraining exp(still have problem)
 +
** pretrain on our libri-keyword dataset(~277h) and finetune on 15-shot GSC dataset with MT
 +
*** top-1 acc --> 9.72%, EER --> 49.73%
 +
** pretrained model still have problem(Maybe audio and pseudo-label duration differ too much)
 
||
 
||
*
+
*  
 
||
 
||
 
*
 
*
第61行: 第71行:
 
|Xiaolou Li
 
|Xiaolou Li
 
||
 
||
*
+
* Reproduce Grouping ViT as the modality projection (trouble in inference)
 +
* Some test on different prompt from ASR paper. [https://z1et6d3xtb.feishu.cn/docx/CpnKdz2ruoVBxOx59wLcT9FYnSg?from=from_copylink]
 +
* Paper reading (mainly about ASR + LLM and multimodality projection method)
 
||
 
||
 
*
 
*
第72行: 第84行:
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
*
+
*CNVSRC 2024 things
 +
*Reading some Speech-separation papper
 
||
 
||
 
*
 
*
第83行: 第96行:
 
|Pengqi Li
 
|Pengqi Li
 
||
 
||
*
+
* Analysis ongoing for pooling with condition(difficult to explain)
 
||
 
||
 
*
 
*
第94行: 第107行:
 
|Wan Lin
 
|Wan Lin
 
||
 
||
*
+
* NS paper: Supplement experimental results and citations
 
||
 
||
 
*
 
*
第105行: 第118行:
 
|Tianhao Wang
 
|Tianhao Wang
 
||
 
||
*
+
* reproducing sound filter (data and code)
 +
* project things
 
||
 
||
 
*
 
*
第116行: 第130行:
 
|Zhenyu Zhou
 
|Zhenyu Zhou
 
||
 
||
*
+
*Model quantification
 
||
 
||
 
*
 
*
第127行: 第141行:
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
*
+
* Neural Scoring
 +
** Revising paper
 +
** Supplement experiments(finished)
 
||
 
||
 
*
 
*
第138行: 第154行:
 
|Jiaying Wang
 
|Jiaying Wang
 
||
 
||
*
+
* reproducing Condition chain code
 
||
 
||
 
*
 
*
第171行: 第187行:
 
|Yang Wei
 
|Yang Wei
 
||
 
||
*
+
* Test KWS model with test set v1.0 (result analysis in progress)
 
||
 
||
 
*
 
*
第181行: 第197行:
 
|Lily
 
|Lily
 
||
 
||
*
+
* Prepare for high shcool summer trip class(last Sunday)
 +
* Prepare for teacher's course (On this Saturday)
 +
* AIradiance's daily work
 
||
 
||
 
*
 
*
第199行: 第217行:
 
|Yue Gu
 
|Yue Gu
 
||
 
||
*
+
* writing paper
 +
* read several accent adaptation papers
 
||
 
||
 
*
 
*
第208行: 第227行:
 
|Qi Qu
 
|Qi Qu
 
||
 
||
*  
+
* AED:
 +
** Classifier trained on "cries" samples.
 +
** Artificial recall test datasets for "slaps" and "cries".
 +
* KWS:
 +
** Mandarin Chinese 48-word recall test dataset: 10 speakers * 10 repeats expected.
 +
* Misc:
 +
** Live talk preparation.
 
||
 
||
 
*
 
*

2024年8月5日 (一) 10:58的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • AC-SQL paper for KDD
  • Several public talks
  • Review for ISCSLP
Lantian Li
  • GPU status [1]
  • AI graph
    • QA slides checked
  • High school handbook (20/40)
Ying Shi
Zhenghai You
  • Fix mutil-scale loss bug in Ex-former(u-net)
  • Tse Project: The performance of the pre-trained model on 12 spk data is poor
  • Writing ICCIP2024 & Complete the experiment
Junming Yuan
  • Hubert pretraining exp(still have problem)
    • pretrain on our libri-keyword dataset(~277h) and finetune on 15-shot GSC dataset with MT
      • top-1 acc --> 9.72%, EER --> 49.73%
    • pretrained model still have problem(Maybe audio and pseudo-label duration differ too much)
Xiaolou Li
  • Reproduce Grouping ViT as the modality projection (trouble in inference)
  • Some test on different prompt from ASR paper. [2]
  • Paper reading (mainly about ASR + LLM and multimodality projection method)
Zehua Liu
  • CNVSRC 2024 things
  • Reading some Speech-separation papper
Pengqi Li
  • Analysis ongoing for pooling with condition(difficult to explain)
Wan Lin
  • NS paper: Supplement experimental results and citations
Tianhao Wang
  • reproducing sound filter (data and code)
  • project things
Zhenyu Zhou
  • Model quantification
Junhui Chen
  • Neural Scoring
    • Revising paper
    • Supplement experiments(finished)
Jiaying Wang
  • reproducing Condition chain code
Yu Zhang
Wenqiang Du
  • primary school handbook (35/46)
Yang Wei
  • Test KWS model with test set v1.0 (result analysis in progress)
Lily
  • Prepare for high shcool summer trip class(last Sunday)
  • Prepare for teacher's course (On this Saturday)
  • AIradiance's daily work
Turi
Yue Gu
  • writing paper
  • read several accent adaptation papers
Qi Qu
  • AED:
    • Classifier trained on "cries" samples.
    • Artificial recall test datasets for "slaps" and "cries".
  • KWS:
    • Mandarin Chinese 48-word recall test dataset: 10 speakers * 10 repeats expected.
  • Misc:
    • Live talk preparation.