ASR:2015-05-18 - 版本历史

Lr：/* binary vector */

2015-05-25T00:59:09Z

‎binary vector

Lr：/* Order representation */

2015-05-25T00:58:26Z

‎Order representation

Lr：/* Stochastic ListNet */

2015-05-25T00:57:35Z

‎Stochastic ListNet

Lr：/* Translation */

2015-05-25T00:56:46Z

‎Translation

Lr：/* relation classifier */

2015-05-25T00:56:05Z

‎relation classifier

Zxw：/* Speech Processing */

2015-05-20T08:58:23Z

‎Speech Processing

Zxw：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

2015-05-20T07:16:02Z

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====
*character-lm rnn(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.
:* result:wer:70%-50% on top1.
:* change the AM model

===Order representation ===
* modify the objective function
* sup-sampling method to solve the low frequence word
===binary vector===

===Stochastic ListNet===
* using sampling method and test

===relation classifier===
* test the bidirectional neural network(B-RNN) and get a little improvement

===plan to do===
* combine LDA with neural network

←上一版本		2015年5月25日 (一) 00:59的版本
第74行：		第74行：

	===binary vector===		===binary vector===
		+	*Finish hamming metric binary vector.
		+	*Try to finish binary vector.
		+	*Do test report.

	===Stochastic ListNet===		===Stochastic ListNet===

@@ 第70行： / 第70行： @@
 * modify the objective function
 * sup-sampling method to solve the low frequence word
 ===binary vector===

@@ 第73行： / 第73行： @@
 ===Stochastic ListNet===
-* using sampling method and test
+*To finish writing first edition of emnlp 2015 long paper
 ===relation classifier===

@@ 第65行： / 第65行： @@
 * CNN adapt to resolve the low resource problem
 ===Translation===
-* similar-pair method in English word using translation model.
+*Test the performance of the similar-pair method in bilingual recognition
-:* result:wer:70%-50% on top1.
-:* change the AM model
 ===Order representation ===

@@ 第78行： / 第78行： @@
 ===relation classifier===
-* test the  bidirectional neural network(B-RNN) and get a little improvement
+*Tune the best model.
 ===plan to do===
 * combine LDA with neural network

@@ 第4行： / 第4行： @@
 ==== Environment ====
 * grid-15 often does not work
 ==== RNN AM====
@@ 第10行： / 第11行： @@
 * run using wsj,MPE  --Chao Liu
 * run bi-directon --Chao Liu
-* modify code --Zhiyuan
+* train RNN with dark knowledge transfer on AURORA4 --zhiyuan
 ==== Mic-Array ====
 * Change the prediction from  fbank to spectrum features
 * investigate alpha parameter in time domian and frquency domain
@@ 第20行： / 第23行： @@
 ====RNN-DAE(Deep based Auto-Encode-RNN)====
-* HOLD --Zhiyong Zhang
+* 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===
-:* DNN-based sid --Yiye Lin
+* 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
+*  hold --Tian Lan
-:* Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
+* 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.
+* 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
+* Ivector dimention is smaller, performance is better
-:* Augument to hidden layer is better than input layer
+* Augument to hidden layer is better than input layer
-:* train on wsj(testbase dev93+evl92)
+* train on wsj(testbase dev93+evl92)
 ===Dark knowledge===
-:* Ensemble using 100h dataset to construct diffrernt structures -- Mengyuan
+* 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
+:*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
+* adaptation English and Chinglish
-::* Try to improve the chinglish performance extremly
+:* Try to improve the chinglish performance extremly
-:* unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
+* unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
-::* test large database with AMIDA
+* 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==