“ASR:2015-06-01”版本间的差异
来自cslt Wiki
（→Text Processing） |
|||
| （2位用户的2个中间修订版本未显示） | |||
| 第3行： | 第3行： | ||
==== Environment ==== | ==== Environment ==== | ||
| − | * grid-15 | + | * grid-15 and grid-11 run slowly or do not work |
| − | + | ||
==== RNN AM==== | ==== RNN AM==== | ||
| 第23行： | 第22行： | ||
====RNN-DAE(Deep based Auto-Encode-RNN)==== | ====RNN-DAE(Deep based Auto-Encode-RNN)==== | ||
| + | * hold | ||
* deliver to mengyuan | * deliver to mengyuan | ||
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261 | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261 | ||
===Speaker ID=== | ===Speaker ID=== | ||
| − | * DNN-based sid -- | + | * DNN-based sid --Tian Lan |
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327 | :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327 | ||
| 第62行： | 第62行： | ||
====W2V based document classification==== | ====W2V based document classification==== | ||
| − | * | + | * APSP paper |
* CNN adapt to resolve the low resource problem | * CNN adapt to resolve the low resource problem | ||
===Translation=== | ===Translation=== | ||
| − | * | + | * draft paper of journal |
===Order representation === | ===Order representation === | ||
| − | * | + | * modify the objective function(hold) |
| − | * | + | * sup-sampling method to solve the low frequence word(hold) |
| + | * journal paper | ||
===binary vector=== | ===binary vector=== | ||
| − | * | + | * nips paper |
| − | + | ||
| − | + | ||
| − | + | ||
===Stochastic ListNet=== | ===Stochastic ListNet=== | ||
| − | * | + | *done |
===relation classifier=== | ===relation classifier=== | ||
| − | * | + | *done |
===plan to do=== | ===plan to do=== | ||
* combine LDA with neural network | * combine LDA with neural network | ||
| − | |||
| − | |||
2015年6月4日 (四) 07:31的最后版本
Speech Processing
AM development
Environment
- grid-15 and grid-11 run slowly or do not work
RNN AM
- details at http://liuc.cslt.org/pages/rnnam.html
- Test monophone on RNN using dark-knowledge --Chao Liu
- run using wsj,MPE --Chao Liu
- run bi-directon --Chao Liu
- train RNN with dark knowledge transfer on AURORA4 --zhiyuan
Mic-Array
- hold
- Change the prediction from fbank to spectrum features
- investigate alpha parameter in time domian and frquency domain
- ALPHA>=0, using data generated by reverber toolkit
- consider theta
- compute EER with kaldi
RNN-DAE(Deep based Auto-Encode-RNN)
- hold
- deliver to mengyuan
Speaker ID
- DNN-based sid --Tian Lan
Ivector&Dvector based ASR
- hold --Tian Lan
- Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
- Direct using the dark-knowledge strategy to do the ivector training.
- Ivector dimention is smaller, performance is better
- Augument to hidden layer is better than input layer
- train on wsj(testbase dev93+evl92)
Dark knowledge
- Ensemble using 100h dataset to construct diffrernt structures -- Mengyuan
- adaptation English and Chinglish
- Try to improve the chinglish performance extremly
- unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
- test large database with AMIDA
- test hidden layer knowledge transfer--xuewei
bilingual recognition
- hold
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang and Mengyuan
language vector
- train DNN with language vector--xuewei
Text Processing
RNN LM
- character-lm rnn(hold)
- lstm+rnn
- check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
W2V based document classification
- APSP paper
- CNN adapt to resolve the low resource problem
Translation
- draft paper of journal
Order representation
- modify the objective function(hold)
- sup-sampling method to solve the low frequence word(hold)
- journal paper
binary vector
- nips paper
Stochastic ListNet
- done
relation classifier
- done
plan to do
- combine LDA with neural network
