“2024-07-22”版本间的差异
来自cslt Wiki
| （10位用户的17个中间修订版本未显示） | |||
| 第46行： | 第46行： | ||
|Zhenghai You | |Zhenghai You | ||
|| | || | ||
| − | * | + | * Reproduce DPRNN-IRA[https://z1et6d3xtb.feishu.cn/docx/EcNmdXC2Uo7Egdx5UvWcvaFgnr2] |
| + | * TSE Project: Targetless model with tSDR and tMSE Loss | ||
|| | || | ||
* | * | ||
| 第78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90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 | + | *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113行： | 第117行： | ||
|Wan Lin | |Wan Lin | ||
|| | || | ||
| − | * | + | * NS paper writing [https://z1et6d3xtb.feishu.cn/docx/WNYJddKBBo6dHtxcszZcuBbBnXc?from=from_copylink] |
|| | || | ||
* | * | ||
| 第137行： | 第141行： | ||
|Zhenyu Zhou | |Zhenyu Zhou | ||
|| | || | ||
| − | * | + | *TSE stream test[https://z1et6d3xtb.feishu.cn/docx/AVKSdXxJooSgfXxbYW1c1lNrnab] |
| + | *Multi-speaker SS Paper reading | ||
|| | || | ||
* | * | ||
| 第148行： | 第153行： | ||
|Junhui Chen | |Junhui Chen | ||
|| | || | ||
| − | * | + | * NS paper writing |
|| | || | ||
* | * | ||
| 第159行： | 第164行： | ||
|Jiaying Wang | |Jiaying Wang | ||
|| | || | ||
| − | * | + | * change to chain-based methods |
| + | ** reproducing sequence to multi-sequence code | ||
| + | ** read related papers | ||
| + | |||
|| | || | ||
* | * | ||
| 第170行： | 第178行： | ||
|Yu Zhang | |Yu Zhang | ||
|| | || | ||
| − | * | + | * AED: |
| + | ** retraining model without dilation convolution | ||
| + | ** assist Huawei in model quantization and engineering | ||
| + | * Finance: | ||
| + | ** retraining model with data totally align with JunWang | ||
|| | || | ||
* | * | ||
| 第181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192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230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
| 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 |
|
|
|
