ASR:2015-05-11 - 版本历史

Lr：/* RNN LM */

2015-05-18T01:24:28Z

‎RNN LM

Lr：/* Text Processing */

2015-05-18T01:23:38Z

‎Text Processing

Lr：/* Text Processing */

2015-05-18T01:21:21Z

‎Text Processing

Lr：/* Translation */

2015-05-11T02:36:45Z

‎Translation

Lr：/* Stochastic ListNet */

2015-05-11T02:29:41Z

‎Stochastic ListNet

Lr：/* relation classifier */

2015-05-11T02:29:24Z

‎relation classifier

Lr：/* Text Processing */

2015-05-11T02:08:46Z

‎Text Processing

Lr：/* Sparse code in NLP */

2015-05-11T01:50:45Z

‎Sparse code in NLP

Lr：以“==Speech Processing == === AM development === ==== Environment ==== * grid-15 often does not work ==== RNN AM==== * details at http://liuc.cslt.org/pages/rnnam.htm...”为内容创建页面

2015-05-11T00:55:05Z

以“==Speech Processing == === AM development === ==== Environment ==== * grid-15 often does not work ==== RNN AM==== * details at http://liuc.cslt.org/pages/rnnam.htm...”为内容创建页面

新页面

==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===
:* DNN-based sid --Yiye Lin
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327

===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
::*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --Zhiyong Zhang
:* 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
*

←上一版本		2015年5月18日 (一) 01:23的版本
第72行：		第72行：
	===relation classifier===		===relation classifier===
	* test the bidirectional neural network(B-RNN) and get a little improvement		* test the bidirectional neural network(B-RNN) and get a little improvement
		+
		+	===plan to do===
		+	* combine LDA with neural network

@@ 第66行： / 第66行： @@
 ===Stochastic ListNet===
-* using sampling method
+* using sampling method and test
 ===relation classifier===
 * test the  bidirectional neural network(B-RNN) and get a little improvement

←上一版本		2015年5月11日 (一) 02:29的版本
第69行：		第69行：

	===relation classifier===		===relation classifier===
−	* ~~majority of error in others class~~	+	* test the bidirectional neural network(B-RNN) and get a little improvement
−	*	+

@@ 第49行： / 第49行： @@
 ==Text Processing==
 ====RNN LM====
-*rnn
+*character-lm rnn(hold)
-:* 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)

@@ 第65行： / 第65行： @@
 * modify the objective function
 * sup-sampling method to solve the low frequence word
-* learn binary vector
+===binary vector===
 ===Stochastic ListNet===

@@ 第59行： / 第59行： @@
 ===Translation===
 * similar-pair method in English word using translation model.
 ===Order representation ===