“ASR Status Report 2017-8-14”版本间的差异
来自cslt Wiki
Wangyanqing(讨论 | 贡献) |
|||
(5位用户的12个中间修订版本未显示) | |||
第6行: | 第6行: | ||
|Xiaofei Kang | |Xiaofei Kang | ||
|| | || | ||
− | * | + | * Recording 35 people audio, located in /work7/zhangmiao/speaker/wavdata/data_new |
+ | * Learn the new test website from zhangmiao | ||
|| | || | ||
− | * | + | * Go home with my mom, and come back on Friday night. |
|- | |- | ||
第15行: | 第16行: | ||
|Miao Zhang | |Miao Zhang | ||
|| | || | ||
− | * | + | * Recording work |
+ | * Test website's data preparation | ||
+ | * check the linear chapter | ||
|| | || | ||
− | * | + | * Continue to record |
+ | * do experiments on recorded speech if possible | ||
+ | * check the NN chapter | ||
|- | |- | ||
第24行: | 第29行: | ||
|Yanqing Wang | |Yanqing Wang | ||
|| | || | ||
− | * TRP uploaded. | + | * [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/50/Connection_Sparseness.pdf TRP] uploaded. |
* explore the importance of sparseness structure: | * explore the importance of sparseness structure: | ||
− | ** After pruning, initialize randomly. | + | ** After pruning, initialize non-zero values randomly, train. |
** train nnet with 177-dimension hidden layer. | ** train nnet with 177-dimension hidden layer. | ||
** [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=wangyanqing&step=view_request&cvssid=609 result] | ** [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=wangyanqing&step=view_request&cvssid=609 result] | ||
|| | || | ||
− | * | + | * continue exploring the values of trained nnet. |
|- | |- | ||
第37行: | 第42行: | ||
|Ying Shi | |Ying Shi | ||
|| | || | ||
− | * | + | * general codeMap finished(kazak) |
+ | * crawler program delayed(Most of the kazakh website is down. I will cralw data from overseas websites) | ||
|| | || | ||
− | * | + | * collect more Unicode. such as Tibetan, Mongolia. |
+ | * crawler kazak data from overseas websites. | ||
|- | |- | ||
第46行: | 第53行: | ||
|Yixiang Chen | |Yixiang Chen | ||
|| | || | ||
− | * | + | * Study English and help Lantian do some Exps. |
|| | || | ||
* | * | ||
|- | |- | ||
+ | |||
|- | |- | ||
|Lantian Li | |Lantian Li | ||
|| | || | ||
− | * | + | * Visualization and quantification for d-vector [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e2/Spk_seg.pdf]. |
− | || | + | ** phone-aware and phone-blind. |
− | * | + | ** within speaker variation and between speaker variation. |
+ | * Speaker segmentation Exps. | ||
+ | || | ||
+ | * Finish speaker segmentation Exp. | ||
+ | * Prepare IS17 presentation. | ||
|- | |- | ||
第63行: | 第75行: | ||
|Zhiyuan Tang | |Zhiyuan Tang | ||
|| | || | ||
− | * | + | * reorganize auto-scoring system, next ??? |
− | || | + | * collecting material (PPT) for Kaldi toolbook. |
− | * | + | || |
+ | * prefer to rewrite the scoring part. | ||
+ | * toolbook writing | ||
|- | |- | ||
第132行: | 第146行: | ||
|Lantian Li | |Lantian Li | ||
|| | || | ||
− | * | + | * Visualization and quantification for d-vector [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e2/Spk_seg.pdf]. |
+ | ** phone-aware and phone-blind. | ||
+ | ** within speaker variation and between speaker variation. | ||
+ | * Lots of trifles. | ||
|| | || | ||
− | * | + | * Speaker segmentation task. |
|- | |- | ||
2017年8月14日 (一) 05:36的最后版本
Date | People | Last Week | This Week |
---|---|---|---|
2017.8.14 | Xiaofei Kang |
|
|
Miao Zhang |
|
| |
Yanqing Wang |
| ||
Ying Shi |
|
| |
Yixiang Chen |
|
| |
Lantian Li |
|
| |
Zhiyuan Tang |
|
|
Date | People | Last Week | This Week |
---|---|---|---|
2017.8.7 | Xiaofei Kang |
|
|
Miao Zhang |
|
| |
Yanqing Wang |
|
| |
Ying Shi |
|
| |
Yixiang Chen |
|
| |
Lantian Li |
|
| |
Zhiyuan Tang |
|
|