ASR:2014-12-29 - 版本历史

2014年12月29日 (一) 08:48 Zhangzy

2014-12-29T08:48:26Z

Lr：/* improve lucene search */

2014-12-29T06:23:52Z

‎improve lucene search

Lr：/* Domain specific LM */

2014-12-29T06:23:16Z

‎Domain specific LM

Lr：以“==Text Processing== ===LM development=== ====Domain specific LM==== * LM2.0 :* data check for lexicon(jietong) :* merge lm with NAME POI etc.(hanzhenglong) :* mix...”为内容创建页面

2014-12-29T05:42:49Z

以“==Text Processing== ===LM development=== ====Domain specific LM==== * LM2.0 :* data check for lexicon(jietong) :* merge lm with NAME POI etc.(hanzhenglong) :* mix...”为内容创建页面

新页面

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

====Domain specific LM====
* LM2.0
:* data check for lexicon(jietong)
:* merge lm with NAME POI etc.(hanzhenglong)
:* mix the sougou2T-lm,kn-discount continue
:* train a large lm using 25w-dict.
:*

* 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
:* modify the paper(yuanb two days),paper submit this week.

====RNN LM====
*rnn
:* test wer RNNLM on Chinese data from jietong-data('''this week''')
:* generate the ngram model from rnnlm and test the ppl with different size txt.[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Jt-chinese#sampling_data_from_rnnlm]
*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.
:* Read Liu's paper.
====relation====
* Accomplish transE with almost the same performance as the paper did(even better)[http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=316:result]
====Character to word====
* Character to word conversion(hold)
:* prepare the task: word similarity
:* prepare the dict.

===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.
::*
====XiaoI framework====
* context in xiaoI
====query normalization====
* using NER to normalize the word

* new inter will install SEMPRE

←上一版本		2014年12月29日 (一) 08:48的版本
第1行：		第1行：
		+	==Speech Processing ==
		+	=== AM development ===
		+
		+	==== Environment ====
		+	* Modification
		+	:* First down-frequency of gpu760
		+	:* Improved the gpu Fan-speed
		+	:* Change the sleep-mode of gpu
		+
		+	* May gpu760 of grid-14 be something wrong. To be exchanged.
		+	* To buy 3*2k PCs.
		+
		+	==== Sparse DNN ====
		+	* details at http://liuc.cslt.org/pages/sparse.html
		+
		+	==== RNN AM====
		+	* Adjusting the learning rate.(+)
		+	* Trying toolkit of Microsoft.(+)
		+	* Trying new LSTM toolkit from Baidu
		+	* details at http://liuc.cslt.org/pages/rnnam.html
		+
		+	==== A new nnet training scheduler ====
		+	* details at http://liuc.cslt.org/pages/nnet-sched.html
		+	* Test 500h dataset, 36-epchs/8-batches --Similar performance observed compared with std recipe
		+	* Test on 36600h dataset --done.
		+
		+	====Dropout & Maxout & Convolutive network====
		+
		+	* Drop out(+)
		+	:** Find and test unknown noise test-data.(++)
		+
		+	* 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
		+
		+	* Convolutive network(DAE)
		+	:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=311
		+	:* To test real enviroment echo.
		+
		+	====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
		+	:* To test real enviroment echo.
		+
		+	====VAD====
		+	* Harmonics and Teager energy features being investigation (++)
		+
		+	====Speech rate training====
		+	:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=268
		+
		+	====Confidence====
		+	* Reproduce the experiments on fisher dataset.
		+	* Use the fisher DNN model to decode all-wsj dataset
		+	* preparing scoring for puqiang data
		+	* HOLD
		+
		+	===Speaker ID===
		+	:* Non-stream GMM:wer-2.28%
		+	seperate3-ivector:wer-3.54 single-ivector:wer-1.57
		+	seperate-PLDA:wer-0.87 single-PLDA:wer-1.00
		+	:* Code ready
		+
		+	===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
		+	* To test 10 language-ids
		+
		+	===Voice Conversion===
		+	* Yiye is reading materials(+)
		+
		+
	==Text Processing==		==Text Processing==
	===LM development===		===LM development===

@@ 第54行： / 第54行： @@
 ====improve lucene search====
 :* add more feature to improve search.
-::*
+::* POS, NER ,tf ,idf ..
 ====XiaoI framework====
 *  context in xiaoI

@@ 第5行： / 第5行： @@
 * LM2.0
 :* data check for lexicon(jietong)
-:* merge lm with NAME POI etc.(hanzhenglong)
+:* merge lm with NAME POI etc.(hanzhenglong/wxx)
 :* mix the sougou2T-lm,kn-discount continue
-:* train a large lm using 25w-dict.
+:* 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