ASR:2015-01-19 - 版本历史

Yinshi：/* RNN-DAE(Deep based Atuo-Encode- RNN) */

2015-01-23T08:48:11Z

‎RNN-DAE(Deep based Atuo-Encode- RNN)

2015年1月23日 (五) 08:47 Yinshi

2015-01-23T08:47:42Z

Lr：/* context framework */

2015-01-23T01:24:04Z

‎context framework

Lr：/* Text Processing */

2015-01-23T01:23:18Z

‎Text Processing

Lr：以“==Speech Processing == === AM development === ==== Environment ==== * May gpu760 of grid-14 be something wrong. To be exchanged. * grid-2 can not be booted * grid-1...”为内容创建页面

2015-01-19T08:32:47Z

以“==Speech Processing == === AM development === ==== Environment ==== * May gpu760 of grid-14 be something wrong. To be exchanged. * grid-2 can not be booted * grid-1...”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.
* grid-2 can not be booted
* grid-10 should replac the CPU fan.

==== Sparse DNN ====
* details at http://liuc.cslt.org/pages/sparse.html

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

====Dropout & Maxout & retifier ====
* Drop out

* 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)====
:* Technical report to draft, Mengyuan Zhao and Zhiyong Zhang.
:* To test real enviroment echo.
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=318
:* XueWei will reproduce the experiments.

====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====
* Harmonics and Teager energy features done.
* Frame energy Model training done.
* Other features model to be train.

====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
* HOLD

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

====Domain specific LM====
* LM2.1
:* mix the sougou2T-lm,kn-discount continue
:* train a large lm using 25w-dict.(hanzhenglong/wxx)
::* data pre-processing("this week")

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

====tag LM====
* Tag Lm
:* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong ("this month")
*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
:* 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====
* data prepare.
====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 ..

====context framework====
* code for organization
====query normalization====
* using NER to normalize the word

* new inter will install SEMPRE

@@ 第37行： / 第37行： @@
 :* XueWei will reproduce the experiments.
-====RNN-DAE(Deep based Atuo-Encode- RNN)====
+====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
 :* HOLD

@@ 第4行： / 第4行： @@
 ==== Environment ====
 * May gpu760 of grid-14 be something wrong. To be exchanged.
-* grid-2 can not be booted
+* grid-11 often shutdown automatically
-* grid-10 should replac the CPU fan.
+* grid-2/grid-10 have replaced the CPU fan.
 ==== Sparse DNN ====
@@ 第26行： / 第27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.(+)
 ====DNN-DAE(Deep Atuo-Encode-DNN)====
 :* Technical report to draft, Mengyuan Zhao and Zhiyong Zhang.
 :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=318
 :* XueWei will reproduce the experiments.
@@ 第40行： / 第39行： @@
 ====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====
-* Harmonics and Teager energy features done.
+* Harmonics and Teager energy features.
-* Frame energy Model training done.
+* MPE training
-* Other features model to be train.
+* Test only Harmonic feature
 ====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====

@@ 第134行： / 第134行： @@
 ====context framework====
-*  code for organization
+* code for organization
-::* change to knowledge graph
+:* change to knowledge graph
 ====query normalization====
 * using NER to normalize the word
 * new inter will install SEMPRE

@@ 第81行： / 第81行： @@
 :* mix the sougou2T-lm,kn-discount continue
 :* train a large lm using 25w-dict.(hanzhenglong/wxx)
-::* data pre-processing("this week")
+::* find the problem in asr result
+::* the model will finish (Tuesday)
-* new dict.
-:*  dongxu help zhenglong with large dictionary.
 ====tag LM====
 * Tag Lm
 :* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong ("this month")
 *paper
 :* paper submit this week.
@@ 第94行： / 第93行： @@
 :* find similarity word using word2vec,word vector is training.
 :* set the weight for word
 ====RNN LM====
@@ 第109行： / 第110行： @@
 * Knowledge vector
 :* Make a proper test set.
-:*
+:* use text information and train word vector together.
 :* Modify the object function and training process.
+:* try to train on the whole data set
-====relation====
+* result
 ====Character to word====
 * Character to word conversion(hold)
@@ 第119行： / 第121行： @@
 * v5.0 demo released
 :* cut the dict and use new segment-tool
 ===QA===
@@ 第126行： / 第131行： @@
 :* add more feature to improve search.
 ::* POS, NER ,tf ,idf ..
 ====context framework====
 *  code for organization
 ====query normalization====
 * using NER to normalize the word
 * new inter will install SEMPRE