“2025-05-12”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（15位用户的17个中间修订版本未显示）
第6行： 第6行：
 
|Dong Wang
 
|Dong Wang
 
||
 
||
−
* Jiaoyubu's AI lesson
+
* Training at Tsinghua Primary School
 +
* Training for Zhong Lv group
 +
* Training for Beijing 4th Middle School
 +
* AI education material for college school
 +
 
 
||
 
||
 
*
 
*
第17行： 第21行：
 
|Lantian Li
 
|Lantian Li
 
||
 
||
−
*  
+
* Tackle the Huawei Spark Award
 +
* Review graduate theses
 +
* Engage in several academic visits
 
||
 
||
 
*
 
*
第28行： 第34行：
 
|Ying Shi
 
|Ying Shi
 
||
 
||
−
*  
+
* Huawei Spark Award
 
||
 
||
 
*  
 
*  
第40行： 第46行：
 
|Zhenghai You
 
|Zhenghai You
 
||
 
||
−
*  
+
* Completed the delivery of Huawei TSE project
 
||
 
||
 
*
 
*
第50行： 第56行：
 
|Junming Yuan
 
|Junming Yuan
 
||
 
||
−
*  
+
* Revise MT-HuBERT paper v0.2(done)
 +
* Need extend ASR finetuning exp:
 +
** clean finetuning on LS100: LER-->4.17% on test-clean
 +
** mix finetuning is in progress. 
 
||
 
||
 
*
 
*
第61行： 第70行：
 
|Xiaolou Li
 
|Xiaolou Li
 
||
 
||
−
*  
+
* Added new function to VTS Web, enabling ACC2Speech model choosing
 +
* Polished the presentation slide
 +
* Audited a part of our data between 1 January to 7 April
 
||
 
||
 
*  
 
*  
第72行： 第83行：
 
|Zehua Liu
 
|Zehua Liu
 
||
 
||
−
*
+
*Data Verification
 +
*Upload ACC2Lip model to VTS presentation website （with the assistance of Xiaolou）
 +
*Revise presentation PPT and Document according to Sunchang requirement
 
||
 
||
 
*
 
*
第83行： 第96行：
 
|Pengqi Li
 
|Pengqi Li
 
||
 
||
−
*  
+
 
 +
* Review my research (including related papers, code, etc.).
 +
* Organize a pre-experiment to explore the following questions:
 +
** How to visualize
 +
** How to evaluate reliability
 
||
 
||
−
*
+
* Outline of the paper and pre-experiment
 
||
 
||
 
*
 
*
第94行： 第111行：
 
|Wan Lin
 
|Wan Lin
 
||
 
||
−
*  
+
* Writing paper, finish 1st version
 +
* Multi-scaled feature exp: training, haven't observed improvement by far
 
||
 
||
 
*
 
*
第105行： 第123行：
 
|Tianhao Wang
 
|Tianhao Wang
 
||
 
||
−
*  
+
* Huawei huohua award delivery
 
||
 
||
 
*
 
*
第116行： 第134行：
 
|Xiaoxue Luo
 
|Xiaoxue Luo
 
||
 
||
−
*  
+
*read papers and compare the metrics in the audio generation task to select suitable ones to add to our evaluation metrics
 
||
 
||
 
*
 
*
第138行： 第156行：
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
−
*
+
* Writing neural scoring paper
 +
* Reading paper
 
||
 
||
 
*
 
*
第149行： 第168行：
 
|Jiaying Wang
 
|Jiaying Wang
 
||
 
||
−
*
+
* Loss Nan fixed, reason is dimension of linear projection after ctc embedding mismatch the dimension of text label
 +
** after fixed, both linear encoder and conv2d encoder converge well, still training
 +
 
 +
* Network+ preparation
 
||
 
||
 
*
 
*
第160行： 第182行：
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
−
*  
+
* Optimizing Reflection Mechanism (mainly on Rational and The Effective Range of the reflection)
 +
* AED Huawei additional dataset test report delivery (validation model can also reduce the number of parameters on the Huawei dataset)
 
||
 
||
 
*
 
*
第185行： 第208行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*  
+
* Add license check for AIbabel online ASR and KWS (in progress)
 
||
 
||
 
*
 
*
第195行： 第218行：
 
|Turi
 
|Turi
 
||
 
||
−
*  
+
* Graduation documents submission
 +
* Preparing for defense
 
||
 
||
 
*  
 
*  
第212行： 第236行：
 
|Qi Qu
 
|Qi Qu
 
||
 
||
−
*  
+
* Fixed several bugs in converting text-enroll KWS models.
 +
* Some experiments and reports on text-enroll KWS models: [https://b30lttjm7l.feishu.cn/docx/IZlbdBbKpoh5BTxGtlecnMjxnih?from=from_copylink], [https://b30lttjm7l.feishu.cn/docx/Vkjtd1cjboDD3Ex1xMGcq38WnQe?from=from_copylink].
 +
* Consolidating `aibabel_utils` library.
 
||
 
||
 
*
 
*

2025年5月12日 (一) 10:55的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Training at Tsinghua Primary School
  • Training for Zhong Lv group
  • Training for Beijing 4th Middle School
  • AI education material for college school
Lantian Li
  • Tackle the Huawei Spark Award
  • Review graduate theses
  • Engage in several academic visits
Ying Shi
  • Huawei Spark Award
Zhenghai You
  • Completed the delivery of Huawei TSE project
Junming Yuan
  • Revise MT-HuBERT paper v0.2(done)
  • Need extend ASR finetuning exp:
    • clean finetuning on LS100: LER-->4.17% on test-clean
    • mix finetuning is in progress.
Xiaolou Li
  • Added new function to VTS Web, enabling ACC2Speech model choosing
  • Polished the presentation slide
  • Audited a part of our data between 1 January to 7 April
Zehua Liu
  • Data Verification
  • Upload ACC2Lip model to VTS presentation website （with the assistance of Xiaolou）
  • Revise presentation PPT and Document according to Sunchang requirement
Pengqi Li
  • Review my research (including related papers, code, etc.).
  • Organize a pre-experiment to explore the following questions:
    • How to visualize
    • How to evaluate reliability
  • Outline of the paper and pre-experiment
Wan Lin
  • Writing paper, finish 1st version
  • Multi-scaled feature exp: training, haven't observed improvement by far
Tianhao Wang
  • Huawei huohua award delivery
Xiaoxue Luo
  • read papers and compare the metrics in the audio generation task to select suitable ones to add to our evaluation metrics
Zhenyu Zhou
Junhui Chen
  • Writing neural scoring paper
  • Reading paper
Jiaying Wang
  • Loss Nan fixed, reason is dimension of linear projection after ctc embedding mismatch the dimension of text label
    • after fixed, both linear encoder and conv2d encoder converge well, still training
  • Network+ preparation
Yu Zhang
  • Optimizing Reflection Mechanism (mainly on Rational and The Effective Range of the reflection)
  • AED Huawei additional dataset test report delivery (validation model can also reduce the number of parameters on the Huawei dataset)
Wenqiang Du
  • Check jiaoyubu's AI lesson
  • Some of the company's work
    • Private deployment of KWS service
    • Iteratively upgrade the KWS model using the online data
Yang Wei
  • Add license check for AIbabel online ASR and KWS (in progress)
Turi
  • Graduation documents submission
  • Preparing for defense
Yue Gu
  • complete the introduction and related work， method is still in progress（50%）
Qi Qu
  • Fixed several bugs in converting text-enroll KWS models.
  • Some experiments and reports on text-enroll KWS models: [1], [2].
  • Consolidating `aibabel_utils` library.
取自“http://index.cslt.org/mediawiki/index.php?title=2025-05-12&oldid=43097”