ASR:2015-04-08 - 版本历史

Lr：/* Text Processing */

2015-04-08T10:50:31Z

‎Text Processing

2015年4月8日 (三) 07:27 Zxw

2015-04-08T07:27:40Z

Zxw：清空页面

2015-04-08T07:27:03Z

清空页面

Zxw：以“目录 [隐藏] 1 Speech Processing 1.1 AM development 1.1.1 Environment 1.1.2 RNN AM 1.1.3 Mic-Array 1.1.4 Convolutive network 1.1.5 RNN-DAE(Deep based Auto-Encode...”为内容创建页面

2015-04-08T07:26:39Z

以“目录 [隐藏] 1 Speech Processing 1.1 AM development 1.1.1 Environment 1.1.2 RNN AM 1.1.3 Mic-Array 1.1.4 Convolutive network 1.1.5 RNN-DAE(Deep based Auto-Encode...”为内容创建页面

新页面

目录 [隐藏]
1 Speech Processing
1.1 AM development
1.1.1 Environment
1.1.2 RNN AM
1.1.3 Mic-Array
1.1.4 Convolutive network
1.1.5 RNN-DAE(Deep based Auto-Encode-RNN)
1.2 Speaker ID
1.3 Ivector based ASR
2 Text Processing
2.1 tag LM
2.1.1 RNN LM
2.1.2 W2V based doc classification
2.2 Translation
2.3 Sparse NN in NLP
2.4 online learning
Speech Processing[编辑]
AM development[编辑]
Environment[编辑]
grid-11 often shut down automatically, too slow computation speed.

RNN AM[编辑]
details at http://liuc.cslt.org/pages/rnnam.html
tuning parameters on monophone NN
run using wsj,MPE

Mic-Array[编辑]
investigate alpha parameter in time domian and frquency domain
ALPHA>=0

Convolutive network[编辑]
HOLD
CNN + DNN feature fusion
RNN-DAE(Deep based Auto-Encode-RNN)[编辑]
HOLD -Zhiyong
http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261

Speaker ID[编辑]
DNN-based sid --Yiye
Decode --Yiye
http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327
Ivector based ASR[编辑]
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)
Text Processing[编辑]
tag LM[编辑]
similar word extension in FST
check the formula using Bayes and experiment
RNN LM[编辑]
rnn
code the character-lm using Theano
lstm+rnn
check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
W2V based doc classification[编辑]
corpus ready
learn some benchmark.
Translation[编辑]
v5.0 demo released
cut the dict and use new segment-tool
Sparse NN in NLP[编辑]
prepare the ACL
check the code to find the problem .
increase the dimension
use different test set,but the result is not good.
online learning[编辑]
data is ready.prepare the ACL paper
prepare sougouQ data and test it using current online learning method
baseline is not normal.

@@ 第41行： / 第41行： @@
 * similar word extension in FST
 :* check the formula using Bayes and experiment
 ====RNN LM====
@@ 第49行： / 第51行： @@
 ====W2V based doc classification====
-* corpus ready
+* reproducible test using English data
-* learn some benchmark.
+* Code new version spherical word vector.
 ===Translation===
@@ 第58行： / 第61行： @@
 ===Sparse NN in NLP===
 * prepare the ACL
-:* check the code to find the problem .
+:* test result is ok now[http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=344].
-:* increase the dimension
+:* find the new direction.
-:* use different test set,but the result is not good.
 ===online learning===
 * data is ready.prepare the ACL paper
-:* prepare sougouQ data and test it using current online learning method
+:* finish some test.
-:* baseline is not normal.
+:* test the result on different time.

←上一版本	2015年4月8日 (三) 07:27的版本
第1行：	第1行：
	+	==Speech Processing ==
	+	=== AM development ===

	+	==== Environment ====
	+	* grid-11 often shut down automatically, too slow computation speed.
	+
	+
	+	==== RNN AM====
	+	* details at http://liuc.cslt.org/pages/rnnam.html
	+	* tuning parameters on monophone NN
	+	* run using wsj,MPE
	+
	+
	+	==== Mic-Array ====
	+	* investigate alpha parameter in time domian and frquency domain
	+	* ALPHA>=0
	+
	+
	+	====Convolutive network====
	+	* HOLD
	+	:* CNN + DNN feature fusion
	+
	+	====RNN-DAE(Deep based Auto-Encode-RNN)====
	+	* HOLD -Zhiyong
	+	* 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
	+	:* Decode --Yiye
	+	:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327
	+
	+	===Ivector based ASR===
	+	:* 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)
	+
	+	==Text Processing==
	+	===tag LM===
	+	* similar word extension in FST
	+	:* check the formula using Bayes and experiment
	+
	+	====RNN LM====
	+	*rnn
	+	:* code the character-lm using Theano
	+	*lstm+rnn
	+	:* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
	+
	+	====W2V based doc classification====
	+	* corpus ready
	+	* learn some benchmark.
	+
	+	===Translation===
	+	* v5.0 demo released
	+	:* cut the dict and use new segment-tool
	+
	+	===Sparse NN in NLP===
	+	* prepare the ACL
	+	:* check the code to find the problem .
	+	:* increase the dimension
	+	:* use different test set,but the result is not good.
	+
	+	===online learning===
	+	* data is ready.prepare the ACL paper
	+	:* prepare sougouQ data and test it using current online learning method
	+	:* baseline is not normal.

←上一版本		2015年4月8日 (三) 07:27的版本
第1行：		第1行：
−	~~目录 [隐藏]~~
−	~~1 Speech Processing~~
−	~~1.1 AM development~~
−	~~1.1.1 Environment~~
−	~~1.1.2 RNN AM~~
−	~~1.1.3 Mic-Array~~
−	~~1.1.4 Convolutive network~~
−	~~1.1.5 RNN-DAE(Deep based Auto-Encode-RNN)~~
−	~~1.2 Speaker ID~~
−	~~1.3 Ivector based ASR~~
−	~~2 Text Processing~~
−	~~2.1 tag LM~~
−	~~2.1.1 RNN LM~~
−	~~2.1.2 W2V based doc classification~~
−	~~2.2 Translation~~
−	~~2.3 Sparse NN in NLP~~
−	~~2.4 online learning~~
−	~~Speech Processing[编辑]~~
−	~~AM development[编辑]~~
−	~~Environment[编辑]~~
−	~~grid-11 often shut down automatically, too slow computation speed.~~

−	~~RNN AM[编辑]~~
−	~~details at http://liuc.cslt.org/pages/rnnam.html~~
−	~~tuning parameters on monophone NN~~
−	~~run using wsj,MPE~~
−
−	~~Mic-Array[编辑]~~
−	~~investigate alpha parameter in time domian and frquency domain~~
−	~~ALPHA>=0~~
−
−	~~Convolutive network[编辑]~~
−	~~HOLD~~
−	~~CNN + DNN feature fusion~~
−	~~RNN-DAE(Deep based Auto-Encode-RNN)[编辑]~~
−	~~HOLD -Zhiyong~~
−	~~http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261~~
−
−	~~Speaker ID[编辑]~~
−	~~DNN-based sid --Yiye~~
−	~~Decode --Yiye~~
−	~~http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327~~
−	~~Ivector based ASR[编辑]~~
−	~~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)~~
−	~~Text Processing[编辑]~~
−	~~tag LM[编辑]~~
−	~~similar word extension in FST~~
−	~~check the formula using Bayes and experiment~~
−	~~RNN LM[编辑]~~
−	~~rnn~~
−	~~code the character-lm using Theano~~
−	~~lstm+rnn~~
−	~~check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)~~
−	~~W2V based doc classification[编辑]~~
−	~~corpus ready~~
−	~~learn some benchmark.~~
−	~~Translation[编辑]~~
−	~~v5.0 demo released~~
−	~~cut the dict and use new segment-tool~~
−	~~Sparse NN in NLP[编辑]~~
−	~~prepare the ACL~~
−	~~check the code to find the problem .~~
−	~~increase the dimension~~
−	~~use different test set,but the result is not good.~~
−	~~online learning[编辑]~~
−	~~data is ready.prepare the ACL paper~~
−	~~prepare sougouQ data and test it using current online learning method~~
−	~~baseline is not normal.~~