“2024-05-20”版本间的差异
来自cslt Wiki
Duwenqiang（讨论 | 贡献） |
|||
| （9位用户的10个中间修订版本未显示） | |||
| 第23行： | 第23行： | ||
|| | || | ||
* GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh] | * GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh] | ||
| − | * Projects (AED -> | + | * Projects (AED -> Quantization, TSE -> Data analysis & Model training) |
| − | * ASIP-BUPT (NeuralScoring -> Paper, CohortSS -> | + | * ASIP-BUPT (NeuralScoring -> Paper-Exps, CohortSS -> Hold) |
| − | * | + | * My application & HaiNan fund |
|| | || | ||
* | * | ||
| 第36行： | 第36行： | ||
|Ying Shi | |Ying Shi | ||
|| | || | ||
| − | * | + | * Diting Demo |
| + | * Cohort ASR with conditional chain | ||
| + | * [https://z1et6d3xtb.feishu.cn/docx/Mt7adFRZMoDHcwxkeLPcdWTGngf?from=from_copylink group work] | ||
|| | || | ||
* | * | ||
| 第47行： | 第49行： | ||
|Zhenghai You | |Zhenghai You | ||
|| | || | ||
| − | * | + | * Data extension model in session one data |
| + | * Evaluation of mixed speech of targetless speakers | ||
| + | * Model evaluation under different loudness levels[https://z1et6d3xtb.feishu.cn/docx/PBAZdsiSWoq82YxWsu3cCD4Tnte] | ||
|| | || | ||
* | * | ||
| 第83行： | 第87行： | ||
|Xiaolou Li | |Xiaolou Li | ||
|| | || | ||
| − | * | + | * Bi-Mamba exp on cnvsrc-single (48.75%) |
| + | * LRS2, LRS3 dataset preparation | ||
| + | * Bi -Mamba exp on LRS2 (4s and full, slow training) | ||
|| | || | ||
| − | * | + | * try to find a method to do data cleaning |
|| | || | ||
* | * | ||
| 第97行： | 第103行： | ||
* AKVSR + pos_emb + attscore_celoss very promising | * AKVSR + pos_emb + attscore_celoss very promising | ||
* AKVSR(v2.1) + pos_emb > AKVSR + pos_emb | * AKVSR(v2.1) + pos_emb > AKVSR + pos_emb | ||
| − | * NC2024 paper writing | + | * NC2024 paper writing [https://z1et6d3xtb.feishu.cn/docx/ZaTFd3A5EoK982xWBVschloanee?from=from_copylink] |
|| | || | ||
* | * | ||
| 第108行： | 第114行： | ||
|Pengqi Li | |Pengqi Li | ||
|| | || | ||
| − | * | + | * NC papers of Our Group[https://z1et6d3xtb.feishu.cn/docx/M4HHdMPvGo6OHUxdC0pcbLkmnid] |
|| | || | ||
* | * | ||
| 第119行： | 第125行： | ||
|Wan Lin | |Wan Lin | ||
|| | || | ||
| − | * | + | * NS: add enroll condition to test encoder: didn't work |
| + | ** Mix-Vox1-O: 4.94% vs 4.28%(vit) | ||
| + | * Determine the experimental design of NS paper together | ||
|| | || | ||
* | * | ||
| 第130行： | 第138行： | ||
|Tianhao Wang | |Tianhao Wang | ||
|| | || | ||
| − | * | + | * align the toolkit for neural scoring |
| + | * next experimental designing with CJH and LW | ||
|| | || | ||
* | * | ||
| 第188行： | 第197行： | ||
|Wenqiang Du | |Wenqiang Du | ||
|| | || | ||
| − | * Upgrade task for aibabel's new 48 | + | * Upgrade task for aibabel's new 48 words KWS model，Doing |
|| | || | ||
* | * | ||
| 第232行： | 第241行： | ||
|Yue Gu | |Yue Gu | ||
|| | || | ||
| − | * | + | * paper writing: 70% experiment section |
| + | * compelete kespeech baseline | ||
| + | * the training of semantic paraformer is convergent | ||
|| | || | ||
* | * | ||
2024年5月21日 (二) 01:02的最后版本
| People | This Week | Next Week | Task Tracking (DeadLine) |
|---|---|---|---|
| Dong Wang |
|
|
|
| Lantian Li |
|
|
|
| Ying Shi |
|
|
|
| Zhenghai You |
|
|
|
| Junming Yuan |
|
|
|
| Chen Chen |
|
|
|
| Xiaolou Li |
|
|
|
| Zehua Liu |
|
|
|
| Pengqi Li |
|
|
|
| Wan Lin |
|
|
|
| Tianhao Wang |
|
|
|
| Zhenyu Zhou |
|
|
|
| Junhui Chen |
|
|
|
| Jiaying Wang |
|
|
|
| Yu Zhang |
|
|
|
| Wenqiang Du |
|
|
|
| Yang Wei |
|
|
|
| Lily |
|
|
|
| Turi |
|
|
|
| Yue Gu |
|
|
|
| Qi Qu |
|
|
|
