“2024-05-13”版本间的差异
来自cslt Wiki
Duwenqiang(讨论 | 贡献) |
|||
(17位用户的23个中间修订版本未显示) | |||
第6行: | 第6行: | ||
|Dong Wang | |Dong Wang | ||
|| | || | ||
− | * | + | |
+ | * Material preparation for Xinhua Net broadcast | ||
+ | * Several public reports | ||
+ | * Review for Electonics and Applied Science | ||
+ | |||
|| | || | ||
* | * | ||
第28行: | 第32行: | ||
|Ying Shi | |Ying Shi | ||
|| | || | ||
− | * | + | * verify cohort Overlap ASR assumption |
+ | ** Identify the speech component which most similar to the cohort vector ✔ | ||
+ | * [https://z1et6d3xtb.feishu.cn/docx/PBaLdj17ao7mKaxFNPacr3aYn8c?from=from_copylink group work] | ||
|| | || | ||
− | * | + | * cohort + conditional chain Overlap ASR |
|| | || | ||
* | * | ||
第39行: | 第45行: | ||
|Zhenghai You | |Zhenghai You | ||
|| | || | ||
− | * | + | * Speech tests and deliver real test samples for HUAWEI |
+ | * Loudness testing and adjustment of Huawei data[https://z1et6d3xtb.feishu.cn/docx/SFZBdrHafohmQJx1ti7c2RZwnuf] | ||
+ | * Comparative experiments on data expansion | ||
|| | || | ||
* | * | ||
第49行: | 第57行: | ||
|Junming Yuan | |Junming Yuan | ||
|| | || | ||
− | * | + | * Continue to add various data augmentation functions into the code |
+ | * Prepare for live broadcast | ||
|| | || | ||
* | * | ||
第60行: | 第69行: | ||
|Chen Chen | |Chen Chen | ||
|| | || | ||
− | * | + | * attend several interviews for job |
+ | * vii group work [https://z1et6d3xtb.feishu.cn/docx/GwFvdn3nnopuU4xhKUncTxSnnTg?from=from_copylink] | ||
|| | || | ||
* | * | ||
第71行: | 第81行: | ||
|Xiaolou Li | |Xiaolou Li | ||
|| | || | ||
− | * | + | * Video mamba exp (good good) |
+ | ** patch frontend | ||
+ | ** conv3d and resnet3d frontend | ||
+ | * Paper reading | ||
|| | || | ||
− | * | + | * run exp on LRS2 and LRS3 (waiting for email feedback) |
+ | * what is the main difference between these two frontend? (conv3d and resnet3d) | ||
|| | || | ||
* | * | ||
第82行: | 第96行: | ||
|Zehua Liu | |Zehua Liu | ||
|| | || | ||
− | * | + | *AKVSR (cer:49.71%) > baseline(cer: 48.76%) |
+ | **AKVSR + pos_emb (a little worse) | ||
+ | **AKVSR + attention score loss(coding) | ||
|| | || | ||
* | * | ||
第93行: | 第109行: | ||
|Pengqi Li | |Pengqi Li | ||
|| | || | ||
− | * | + | * Jinfu and LiuHuan's Outlines of NC |
|| | || | ||
− | * | + | * XueYing's Outline of NC |
+ | * NC paper of Speech XAI overview | ||
|| | || | ||
* | * | ||
第104行: | 第121行: | ||
|Wan Lin | |Wan Lin | ||
|| | || | ||
− | * | + | * EAASP in Sunine(EER) |
+ | ** EA:4.292(3.106 wespeaker) | ||
+ | ** Mix: 7.733(5.962 wespeaker) | ||
+ | * Add CNN condition in test encoder: currently unsuccessful | ||
|| | || | ||
* | * | ||
第115行: | 第135行: | ||
|Tianhao Wang | |Tianhao Wang | ||
|| | || | ||
− | * | + | * Baseline: SpEx+ with Detection (Failed) |
+ | ** difficult to train because vox2 has a much larger data volume than wsj0 | ||
+ | * Toolkit align: lr scheduler, pooling | ||
+ | ** pooling seems critical (same epoch, NS loss: ASP is 0.16 vs TSP is 0.22) | ||
|| | || | ||
* | * | ||
第137行: | 第160行: | ||
|Junhui Chen | |Junhui Chen | ||
|| | || | ||
− | * | + | * Graduation paper |
+ | * Neural Scoring paper writing | ||
|| | || | ||
* | * | ||
第148行: | 第172行: | ||
|Jiaying Wang | |Jiaying Wang | ||
|| | || | ||
− | * | + | * find bad cases in the test set(gender confusion) |
|| | || | ||
− | * | + | * data analyse |
+ | * focus on cohort outside masker | ||
|| | || | ||
* | * | ||
第159行: | 第184行: | ||
|Yu Zhang | |Yu Zhang | ||
|| | || | ||
− | * | + | * AutoML |
+ | ** EvalML test result[https://z1et6d3xtb.feishu.cn/docx/EDO1dLwHToDqiCxhHf6cLXDVnlb?from=from_copylink] | ||
|| | || | ||
* | * | ||
第170行: | 第196行: | ||
|Wenqiang Du | |Wenqiang Du | ||
|| | || | ||
− | * | + | * Just some project test |
|| | || | ||
* | * | ||
第181行: | 第207行: | ||
|Yang Wei | |Yang Wei | ||
|| | || | ||
− | * | + | * Children MDD challenge |
+ | ** Refine documentation and prepare material for discuss | ||
+ | * Huilan stuff | ||
+ | ** Reduce size of TTS Docker image | ||
|| | || | ||
* | * | ||
第191行: | 第220行: | ||
|Lily | |Lily | ||
|| | || | ||
− | * | + | * AIGraph PPT delivery |
+ | * Thesis | ||
+ | * Perception Experiment | ||
|| | || | ||
* | * | ||
第201行: | 第232行: | ||
|Turi | |Turi | ||
|| | || | ||
− | * | + | * Data Collection |
+ | ** Checking audios | ||
+ | * Class works | ||
|| | || | ||
* | * | ||
第218行: | 第251行: | ||
|Qi Qu | |Qi Qu | ||
|| | || | ||
− | * | + | * KWS |
+ | ** Standardize dataset formats and test routines. | ||
+ | ** Data collection and processing. | ||
|| | || | ||
* | * |
2024年5月13日 (一) 10:54的版本
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 |
|
|
|