“2024-07-22”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（8位用户的10个中间修订版本未显示）
第47行： 第47行：
 
||
 
||
 
* Reproduce DPRNN-IRA[https://z1et6d3xtb.feishu.cn/docx/EcNmdXC2Uo7Egdx5UvWcvaFgnr2]
 
* Reproduce DPRNN-IRA[https://z1et6d3xtb.feishu.cn/docx/EcNmdXC2Uo7Egdx5UvWcvaFgnr2]
−
* TSE Project: Targetless model with MSE Loss
+
* TSE Project: Targetless model with tSDR and tMSE Loss
 
||
 
||
 
*
 
*
第79行： 第79行：
 
|Xiaolou Li
 
|Xiaolou Li
 
||
 
||
−
*
+
* LRS-30h PALR2 (2 epoch result, still training)
 +
** VSR:            30.56%
 +
** Refinement: 30.40%
 +
* Paper reading
 
||
 
||
 
*
 
*
第91行： 第94行：
 
||
 
||
 
*LRS3-30h ICL (CER:30.3 > 29.1）
 
*LRS3-30h ICL (CER:30.3 > 29.1）
−
*LRS3-30h image adaptive mask (CER: 27.70 < 29.1)
+
*LRS3-30h image adaptive mask code
 
*Papper reading[https://z1et6d3xtb.feishu.cn/docx/JBsidACDVojhCaxFQLbcCVbsnAc?from=from_copylink] and Maybe Q-former can be useful
 
*Papper reading[https://z1et6d3xtb.feishu.cn/docx/JBsidACDVojhCaxFQLbcCVbsnAc?from=from_copylink] and Maybe Q-former can be useful
 
||
 
||
第114行： 第117行：
 
|Wan Lin
 
|Wan Lin
 
||
 
||
−
*
+
* NS paper writing [https://z1et6d3xtb.feishu.cn/docx/WNYJddKBBo6dHtxcszZcuBbBnXc?from=from_copylink]
 
||
 
||
 
*
 
*
第150行： 第153行：
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
−
*
+
* NS paper writing
 
||
 
||
 
*
 
*
第190行： 第193行：
 
|Wenqiang Du
 
|Wenqiang Du
 
||
 
||
−
*
+
* Complete the company's model upgrade with Weiyang
 +
** cn + minnanyu + Uyghur
 +
** cn + Uyghur + Kazakh
 +
* primary school handbook (12/46)
 
||
 
||
 
*
 
*
第201行： 第207行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*
+
* AIBabel KWS
 +
** Train a new version of Chinese, Uyghur, Kazakh model. [https://z1et6d3xtb.feishu.cn/docx/UWfJd11gCofyaexMkmJcJ9f7nTc]
 
||
 
||
 
*
 
*
第239行： 第246行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* KWS:
 +
** Documents: data preparation, test method.
 +
** Datasets prepared: 1. Mandarin Chinese mild-accent (20 keywords, 14 persons); 2. FAs from production (150k, from Jul. 1 to Jul. 15).
 +
* AED:
 +
** AudioSet as negative samples.
 
||
 
||
 
*
 
*

2024年7月22日 (一) 11:01的最后版本

  • Finish AIGraph slides check
People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Paper review for ISCSLP
  • AIGraph slides check (37/50)
Lantian Li
  • GPU status [1]
  • Review several chain-based separation papers
  • AI graph
    • Slides checking (23/50)
    • High school handbook (11/40)
  • Submit GTV
  • High school handbook (20/40)
Ying Shi
Zhenghai You
  • Reproduce DPRNN-IRA[2]
  • TSE Project: Targetless model with tSDR and tMSE Loss
Junming Yuan
Chen Chen
Xiaolou Li
  • LRS-30h PALR2 (2 epoch result, still training)
    • VSR: 30.56%
    • Refinement: 30.40%
  • Paper reading
Zehua Liu
  • LRS3-30h ICL (CER:30.3 > 29.1）
  • LRS3-30h image adaptive mask code
  • Papper reading[3] and Maybe Q-former can be useful
Pengqi Li
Wan Lin
  • NS paper writing [4]
Tianhao Wang
  • New task investigation: Sound Filter
  • Neural Scoring: CN-Celeb exps refresh the results
  • project: data washing and generator toolkit
Zhenyu Zhou
  • TSE stream test[5]
  • Multi-speaker SS Paper reading
Junhui Chen
  • NS paper writing
Jiaying Wang
  • change to chain-based methods
    • reproducing sequence to multi-sequence code
    • read related papers
Yu Zhang
  • AED:
    • retraining model without dilation convolution
    • assist Huawei in model quantization and engineering
  • Finance:
    • retraining model with data totally align with JunWang
Wenqiang Du
  • Complete the company's model upgrade with Weiyang
    • cn + minnanyu + Uyghur
    • cn + Uyghur + Kazakh
  • primary school handbook (12/46)
Yang Wei
  • AIBabel KWS
    • Train a new version of Chinese, Uyghur, Kazakh model. [6]
Lily
Turi
  • Completed data collection
  • Trained conformer on full data (100h) for 200 epochs. WER 23.9% on 2hrs of test data.
Yue Gu
  • complete the introduction、related work and 1/3 results of the journal paper (8/9).
Qi Qu
  • KWS:
    • Documents: data preparation, test method.
    • Datasets prepared: 1. Mandarin Chinese mild-accent (20 keywords, 14 persons); 2. FAs from production (150k, from Jul. 1 to Jul. 15).
  • AED:
    • AudioSet as negative samples.
取自“http://cslt.org/mediawiki/index.php?title=2024-07-22&oldid=42056”