“2024-08-26”版本间的差异
来自cslt Wiki
Yuanjunming(讨论 | 贡献) |
|||
(15位用户的27个中间修订版本未显示) | |||
第6行: | 第6行: | ||
|Dong Wang | |Dong Wang | ||
|| | || | ||
− | * | + | * Primary school book (17) |
+ | * College AI education | ||
+ | |||
|| | || | ||
* | * | ||
第17行: | 第19行: | ||
|Lantian Li | |Lantian Li | ||
|| | || | ||
− | * | + | * GPU status [https://z1et6d3xtb.feishu.cn/wiki/XGcGwRK5viJmpRkjH9AczIhynCh] |
+ | *AI primary | ||
+ | ** High school handbook (40/40) | ||
|| | || | ||
* | * | ||
第28行: | 第32行: | ||
|Ying Shi | |Ying Shi | ||
|| | || | ||
− | * | + | * Fenyinta stuff |
+ | * reproduce cohort-SOT overlap ASR and some analysis | ||
+ | * Text enroll keywords spotting intermediate PIT-SOT CTC + high layer cross-attention is in progress [https://z1et6d3xtb.feishu.cn/docx/DI3UdF496ojxCQxTqUycsjDQnxf?from=from_copylink here] | ||
|| | || | ||
* | * | ||
第39行: | 第45行: | ||
|Zhenghai You | |Zhenghai You | ||
|| | || | ||
− | * | + | * Speaker Augument: Completed experiments in Libri2mix, Low SISDR testset lower speaker confusion rate |
+ | * ExFormer: Always inferior to the SOTA[https://z1et6d3xtb.feishu.cn/docx/ZbtsdTGuQo4IXnxuxHXcpvBynoe] | ||
|| | || | ||
* | * | ||
第49行: | 第56行: | ||
|Junming Yuan | |Junming Yuan | ||
|| | || | ||
− | * Confirmed that the performance gap of the 10% is determined by the impact of GPUs. | + | * Confirmed that the performance gap of the 10% is determined by the impact of GPUs[https://z1et6d3xtb.feishu.cn/docx/PaATdHi26oEc0Pxovd4cSyp0nQ2]. |
** To fully reproduce the official model, it would take approximately 32 days. | ** To fully reproduce the official model, it would take approximately 32 days. | ||
* Investigate how to train Hubert with Mix-speech (in progress) | * Investigate how to train Hubert with Mix-speech (in progress) | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|| | || | ||
* | * | ||
第73行: | 第69行: | ||
|Xiaolou Li | |Xiaolou Li | ||
|| | || | ||
− | * | + | * LLM long context test |
+ | * Poster for IS24 | ||
+ | * Paper reading | ||
|| | || | ||
* | * | ||
第84行: | 第82行: | ||
|Zehua Liu | |Zehua Liu | ||
|| | || | ||
− | * | + | *CNVSRC 2024 Website |
+ | *Data transfer to HUAWEI | ||
+ | *LLM in Chinese VSR(In-context-learning) | ||
|| | || | ||
* | * | ||
第95行: | 第95行: | ||
|Pengqi Li | |Pengqi Li | ||
|| | || | ||
− | * | + | * Extend Proposal for 'HOW PHONEMES CONTRIBUTE TO DEEP SPEAKER MODELS?'[https://z1et6d3xtb.feishu.cn/docx/NSjYdWC6JorHKBxoUdxcMzman3f] |
+ | ** Reviewing code, paper. | ||
+ | ** Analyzing di-phones in Audio-Mnist. | ||
+ | ** Start exp with TIMIT dataset. | ||
|| | || | ||
* | * | ||
|| | || | ||
− | * | + | * 9.20(one month) |
|- | |- | ||
第106行: | 第109行: | ||
|Wan Lin | |Wan Lin | ||
|| | || | ||
− | * | + | * Neural Scoring: vox2+voxblink1 [https://z1et6d3xtb.feishu.cn/docx/BywjdkGvNou12sxQ4dAcxYa9noh?from=from_copylink] |
|| | || | ||
* | * | ||
第117行: | 第120行: | ||
|Tianhao Wang | |Tianhao Wang | ||
|| | || | ||
− | * | + | * AudioSep reproducing |
+ | * IS24 poster | ||
|| | || | ||
* | * | ||
|| | || | ||
− | |||
|- | |- | ||
第128行: | 第131行: | ||
|Zhenyu Zhou | |Zhenyu Zhou | ||
|| | || | ||
− | * | + | *Some thinking about onnx quantization[https://z1et6d3xtb.feishu.cn/docx/S9ChdyH7go490txZ2ZHcNjXTn2b] |
|| | || | ||
* | * | ||
第139行: | 第142行: | ||
|Junhui Chen | |Junhui Chen | ||
|| | || | ||
− | * | + | * Neural Scoring: |
+ | ** Vox2+Voxblink-clean test[https://z1et6d3xtb.feishu.cn/docx/BywjdkGvNou12sxQ4dAcxYa9noh#Ro69dyERUoN0HvxOGMWcOJjrnuf] | ||
|| | || | ||
* | * | ||
第150行: | 第154行: | ||
|Jiaying Wang | |Jiaying Wang | ||
|| | || | ||
− | * | + | * re-write conditional chain code(can be finished this week) |
+ | * check wsj data | ||
+ | |||
|| | || | ||
* | * | ||
第161行: | 第167行: | ||
|Yu Zhang | |Yu Zhang | ||
|| | || | ||
− | * | + | * AED engineering problem assist |
+ | * Prepare for report | ||
|| | || | ||
* | * | ||
第172行: | 第179行: | ||
|Wenqiang Du | |Wenqiang Du | ||
|| | || | ||
− | * | + | * Complete the unified format and recheck of Primary school handbook |
− | + | * Write middle school handbook(29-41) | |
− | * | + | * Training Chinese and Cantonese KWS model |
+ | |||
|| | || | ||
* | * | ||
第183行: | 第191行: | ||
|Yang Wei | |Yang Wei | ||
|| | || | ||
− | * | + | * Check the badcase of KWS model test. |
|| | || | ||
* | * | ||
第212行: | 第220行: | ||
|Yue Gu | |Yue Gu | ||
|| | || | ||
− | * | + | * write the introduction |
+ | * test the adaptation model on the same accent data:[https://www.yuque.com/g/shibeiing/angax2/efpdhqvsxdi4phua/collaborator/join?token=ysvAeigXC9KFi4CF&source=doc_collaborator] | ||
+ | (got sick today) | ||
|| | || | ||
* | * | ||
第221行: | 第231行: | ||
|Qi Qu | |Qi Qu | ||
|| | || | ||
− | * | + | * KWS: |
+ | ** zh48 test dataset updated: 29 speakers in 3 locations, ~600 utterances per keyword. | ||
+ | ** Recall ~ FA relations plotted. | ||
|| | || | ||
* | * |
2024年8月26日 (一) 11:03的最后版本
People | This Week | Next Week | Task Tracking (DeadLine) |
---|---|---|---|
Dong Wang |
|
|
|
Lantian Li |
|
|
|
Ying Shi |
|
|
|
Zhenghai You |
|
|
|
Junming Yuan |
|
|
|
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 |
(got sick today) |
|
|
Qi Qu |
|
|
|