“ASR:2015-05-04”版本间的差异
来自cslt Wiki
（→Speech Processing） |
（→Text Processing） |
||
| 第48行： | 第48行： | ||
==Text Processing== | ==Text Processing== | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
====RNN LM==== | ====RNN LM==== | ||
*rnn | *rnn | ||
| − | :* test the ppl and code the character-lm | + | :* test the ppl and code the character-lm(hold) |
*lstm+rnn | *lstm+rnn | ||
:* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold) | :* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold) | ||
====W2V based document classification==== | ====W2V based document classification==== | ||
| − | * | + | * make a technical report about document classification using CNN --yiqiao |
| − | * | + | * CNN adapt to resolve the low resource problem |
| − | + | ||
===Translation=== | ===Translation=== | ||
| − | * | + | * similar-pair method in English word using translation model. |
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
| + | ===Sparse code in NLP=== | ||
| + | * modify the objective function | ||
| + | * sup-sampling method to solve the low frequence word | ||
| + | * learn binary vector | ||
===online learning=== | ===online learning=== | ||
| − | * | + | * using sampling method |
===relation classifier=== | ===relation classifier=== | ||
| − | * | + | * majority of error in others class |
| + | * | ||
2015年5月11日 (一) 00:49的最后版本
Speech Processing
AM development
Environment
- grid-15 often does 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
- modify code --Zhiyuan
Mic-Array
- 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 --Zhiyong Zhang
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261
Speaker ID
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.
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=340
- 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 for chinglish under investigation --Mengyuan Zhao
- Try to improve the chinglish performance extremly
- unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
- test large database with AMIDA
bilingual recognition
- http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang and Mengyuan
Text Processing
RNN LM
- rnn
- test the ppl and code the character-lm(hold)
- lstm+rnn
- check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
W2V based document classification
- make a technical report about document classification using CNN --yiqiao
- CNN adapt to resolve the low resource problem
Translation
- similar-pair method in English word using translation model.
Sparse code in NLP
- modify the objective function
- sup-sampling method to solve the low frequence word
- learn binary vector
online learning
- using sampling method
relation classifier
- majority of error in others class
