“2024-08-12”版本间的差异
来自cslt Wiki
| （10位用户的12个中间修订版本未显示） | |||
| 第6行： | 第6行： | ||
|Dong Wang | |Dong Wang | ||
|| | || | ||
| − | * | + | * KDD paper done |
| + | * ISCSLP review done | ||
| + | * Public talk (primary schools) done | ||
| + | |||
| + | |||
|| | || | ||
* | * | ||
| 第17行： | 第21行： | ||
|Lantian Li | |Lantian Li | ||
|| | || | ||
| − | * | + | * GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh] |
| + | * Projects | ||
| + | ** Proposal of DiTing3.0 Phase 2th | ||
| + | * AI graph | ||
| + | ** High school demo lecture | ||
| + | ** High school handbook (16/40) | ||
|| | || | ||
| − | * | + | * High school handbook (22/40) |
|| | || | ||
| − | * | + | * |
|- | |- | ||
| + | |||
| + | |||
| 第28行： | 第39行： | ||
|Ying Shi | |Ying Shi | ||
|| | || | ||
| − | * | + | * Text enroll keywords spotting |
| + | ** cross attention at low layer (95%/4%) | ||
| + | ** corss attention at high layer (92%/6%) | ||
| + | * Conditional-Chain overlap ASR | ||
| + | * group work [https://z1et6d3xtb.feishu.cn/docx/Vr5UdIjvvohB6zxr5mXc3X95nJc?from=from_copylink] | ||
|| | || | ||
* | * | ||
| 第72行： | 第87行： | ||
|Xiaolou Li | |Xiaolou Li | ||
|| | || | ||
| − | * | + | * Long context test |
| + | * Paper reading (memory of LLM) | ||
|| | || | ||
* | * | ||
| 第83行： | 第99行： | ||
|Zehua Liu | |Zehua Liu | ||
|| | || | ||
| − | * | + | *CNVSRC 2024 Technical Report and some CNVSRC 2024 stuff |
|| | || | ||
* | * | ||
| 第105行： | 第121行： | ||
|Wan Lin | |Wan Lin | ||
|| | || | ||
| − | * | + | * prepare training NS model in VoxBlink |
|| | || | ||
* | * | ||
| 第116行： | 第132行： | ||
|Tianhao Wang | |Tianhao Wang | ||
|| | || | ||
| − | * | + | * prepare VGGSound and WavCaps data |
| + | * fix bugs for CLIPSep(ICLR2023) reproducing | ||
|| | || | ||
* | * | ||
| 第127行： | 第144行： | ||
|Zhenyu Zhou | |Zhenyu Zhou | ||
|| | || | ||
| − | * | + | *Model quantification does not work |
|| | || | ||
* | * | ||
| 第138行： | 第155行： | ||
|Junhui Chen | |Junhui Chen | ||
|| | || | ||
| − | * | + | * prepare training NS model in VoxBlink |
|| | || | ||
* | * | ||
| 第149行： | 第166行： | ||
|Jiaying Wang | |Jiaying Wang | ||
|| | || | ||
| − | * | + | * conditional chain on libri2mix（training） |
|| | || | ||
* | * | ||
| 第160行： | 第177行： | ||
|Yu Zhang | |Yu Zhang | ||
|| | || | ||
| − | * | + | * AED engineering problem assist |
| + | ** train model with max pooling instead of avg pooling aim to tackle mismatch between training trunk size and test trunk size (no significant improvement) | ||
| + | ** data aug with wind noise | ||
| + | * paper reading about (Spatial)TimeSeries-LLM | ||
|| | || | ||
* | * | ||
| 第183行： | 第203行： | ||
|Yang Wei | |Yang Wei | ||
|| | || | ||
| − | * | + | * Test KWS model (Chinese+Uyghur+Kazakh; Chinese+Minnan+Uyghur) https://z1et6d3xtb.feishu.cn/docx/MtTcd7xfuoLhcVx3nDocrphinmd?from=create_suite_copy |
|| | || | ||
* | * | ||
| 第220行： | 第240行： | ||
|Qi Qu | |Qi Qu | ||
|| | || | ||
| − | * | + | * KWS: |
| + | ** zh48 (Mandarin Chinese 48 keywords) test dataset annotated. | ||
| + | ** Test across models: keyword-wise ROC. | ||
|| | || | ||
* | * | ||
2024年8月19日 (一) 09:34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 |
|
|
|
