ASR:2015-01-12 - 版本历史

Zhangzy：/* RNN-DAE(RNN based Atuo-Encode) */

2015-01-16T10:31:56Z

‎RNN-DAE(RNN based Atuo-Encode)

2015年1月16日 (五) 10:26 Zhangzy

2015-01-16T10:26:49Z

2015年1月16日 (五) 10:07 Zhangzy

2015-01-16T10:07:06Z

2015年1月16日 (五) 07:54 Zhangzy

2015-01-16T07:54:54Z

Lr：/* Knowledge vector */

2015-01-12T04:42:50Z

‎Knowledge vector

Lr：/* tag LM */

2015-01-12T04:41:02Z

‎tag LM

Lr：/* Text Processing */

2015-01-12T04:40:30Z

‎Text Processing

Lr：以“==Speech Processing == === AM development === ==== Environment ==== * May gpu760 of grid-14 be something wrong. To be exchanged. ==== Sparse DNN ==== * details at...”为内容创建页面

2015-01-12T04:15:36Z

以“==Speech Processing == === AM development === ==== Environment ==== * May gpu760 of grid-14 be something wrong. To be exchanged. ==== Sparse DNN ==== * details at...”为内容创建页面

新页面

==Speech Processing ==
=== AM development ===

==== Environment ====
* May gpu760 of grid-14 be something wrong. To be exchanged.

==== Sparse DNN ====
* details at http://liuc.cslt.org/pages/sparse.html
* need to test clean data
* MPE training to be continue

==== RNN AM====
* Trying toolkit of Microsoft.(+)
* details at http://liuc.cslt.org/pages/rnnam.html

====Dropout & Maxout & retifier ====
* Drop out
:* Change the test data to more noisy data, to verify the effectiveness of dropout.

* MaxOut && P-norm
:* Need to solve the too small learning-rate problem
:** Add one normalization layer after the pnorm-layer
:** Add L2-norm upper bound
:* hold

====Convolutive network====
* Convolutive network(DAE)
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=311
:* Feature extractor
:** Combined with raw features, better performance obsearved.
:** Technical report to draft, Yiye Lin, Shi Yin, Menyuan Zhao and Mian Wang
:* To test real enviroment echo.

====DNN-DAE(Deep Atuo-Encode-DNN)====
:* test on XinWenLianBo music. results on
:** http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhaomy&step=view_request&cvssid=318
:** Technical report to draft, Mengyuan Zhao and Zhiyong Zhang.
:* To test real enviroment echo.

====VAD====
* Harmonics and Teager energy features done.
* Model to be trained.

====Speech rate training====
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=268
:* Technical report to draft. Shi Yin

====Confidence====
* Reproduce the experiments on fisher dataset.
* Use the fisher DNN model to decode all-wsj dataset
* preparing scoring for puqiang data
* HOLD

====Neural network visulization====
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=324

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

===Language ID===
* GMM-based language is ready.
* Delivered to Jietong
* Prepare the test-case
* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=328

===Voice Conversion===
* Yiye is reading materials(+)

==Text Processing==
===LM development===

====Domain specific LM====
* LM2.0
:* mix the sougou2T-lm,kn-discount continue
:* train a large lm using 25w-dict.(hanzhenglong/wxx)
:* prun history lm(wxx)

* new dict.
:* dongxu help zhenglong with large dictionary.

====tag LM====
* need to do
:* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong (hold)
:paper
:* paper submit this week.

====RNN LM====
*rnn
:* test wer RNNLM on Chinese data from jietong-data
:* generate the ngram model from rnnlm and test the ppl with different size txt.
*lstm+rnn
:* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)

===Word2Vector===

====W2V based doc classification====

* Initial results variable Bayesian GMM obtained. Performance is not as good as the conventional GMM.(hold)
* Non-linear inter-language transform: English-Spanish-Czch: wv model training done, transform model on investigation
====Knowledge vector====
* Knowledge vector
:* Make a proper test set.
:* Modify the object function and training process.
====relation====
====Character to word====
* Character to word conversion(hold)
===Translation===

* v5.0 demo released
:* cut the dict and use new segment-tool

===QA===
====improve fuzzy match====
* add Synonyms similarity using MERT-4 method(hold)
====improve lucene search====
:* add more feature to improve search.
::* POS, NER ,tf ,idf ..

====XiaoI framework====
* context in xiaoI
* make a report
====query normalization====
* using NER to normalize the word

* new inter will install SEMPRE

@@ 第38行： / 第38行： @@
 :* XueWei will reproduce the experiments.
-====RNN-DAE(RNN based Atuo-Encode)====
+====RNN-DAE(Deep based Atuo-Encode- RNN)====
 :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261
 ====VAD====

←上一版本		2015年1月16日 (五) 10:26的版本
第71行：		第71行：

	===Voice Conversion===		===Voice Conversion===
−	* Yiye is reading materials~~(+)~~	+	* Yiye is reading materials
		+	* HOLD

@@ 第84行： / 第84行： @@
 * Tag Lm
 :* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong ("this month")
-:paper
+*paper
 :* paper submit this week.
 * similar word extension in FST
 :* find similarity word using word2vec,word vector is training.
 :* set the weight for word
 ====RNN LM====
 *rnn

@@ 第5行： / 第5行： @@
 * May gpu760 of grid-14 be something wrong. To be exchanged.
 * grid-2 can not be booted
 ==== Sparse DNN ====
 * details at http://liuc.cslt.org/pages/sparse.html
 ==== RNN AM====
@@ 第17行： / 第16行： @@
 ====Dropout & Maxout & retifier ====
 * Drop out
-* MaxOut && P-norm
+* MaxOut && P-norm(+)
 :* Need to solve the too small learning-rate problem
 :** Add one normalization layer after the pnorm-layer
@@ 第28行： / 第26行： @@
 * Convolutive network(DAE)
 :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=311
 :* Feature extractor
 :** Combined with raw features, better performance obsearved.
-:** Technical report to draft, Yiye Lin, Shi Yin, Menyuan Zhao and Mian Wang
+:** Technical report to draft, Yiye Lin, Shi Yin, Menyuan Zhao and Mian Wang(+)
-:* To test real enviroment echo.
+:* To test real enviroment echo.(+)
 ====DNN-DAE(Deep Atuo-Encode-DNN)====
-:* test on XinWenLianBo music. results on
+:* Technical report to draft, Mengyuan Zhao and Zhiyong Zhang.
-:** http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhaomy&step=view_request&cvssid=318
-:** Technical report to draft, Mengyuan Zhao and Zhiyong Zhang.
 :* To test real enviroment echo.
 ====VAD====
 * Harmonics and Teager energy features done.
-* Model to be trained.
+* Frame energy Model training done.
 ====Speech rate training====

@@ 第106行： / 第106行： @@
 :*
 :* Modify the object function and training process.
 ====relation====
 ====Character to word====

@@ 第73行： / 第73行： @@
 ====Domain specific LM====
-* LM2.0
+* LM2.1
 :* mix the sougou2T-lm,kn-discount continue
 :* train a large lm using 25w-dict.(hanzhenglong/wxx)
-:* prun history lm(wxx)
+::* data pre-processing("this week")
 * new dict.
@@ 第82行： / 第82行： @@
 ====tag LM====
-* need to do
+* Tag Lm
-:* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong (hold)
+:* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong ("this month")
 :paper
 :* paper submit this week.
+* similar word extension in FST
 ====RNN LM====
 *rnn
@@ 第97行： / 第99行： @@
 ====W2V based doc classification====
+* data prepare.
-* Initial results variable Bayesian GMM obtained. Performance is not as good as the conventional GMM.(hold)
-* Non-linear inter-language transform: English-Spanish-Czch: wv model training done, transform model on investigation
 ====Knowledge vector====
 * Knowledge vector
 :* Make a proper test set.
 :* Modify the object function and training process.
 ====relation====
@@ 第119行： / 第120行： @@
 ::* POS, NER ,tf ,idf ..
-====XiaoI framework====
+====context framework====
-*  context in xiaoI
+*  code for organization
-*  make a report
 ====query normalization====
 * using NER to normalize the word
 * new inter will install SEMPRE