ASR:2014-12-08 - 版本历史

2014年12月8日 (一) 08:43 Zhaomy

2014-12-08T08:43:59Z

Lr：/* Domain specific LM */

2014-12-08T02:22:58Z

‎Domain specific LM

Lr：/* Domain specific LM */

2014-12-08T02:22:13Z

‎Domain specific LM

Lr：/* Domain specific LM */

2014-12-08T02:21:49Z

‎Domain specific LM

Lr：/* Domain specific LM */

2014-12-08T02:21:24Z

‎Domain specific LM

Lr：/* Domain specific LM */

2014-12-08T02:21:07Z

‎Domain specific LM

Lr：/* XiaoI framework */

2014-12-08T02:17:14Z

‎XiaoI framework

Lr：/* QA */

2014-12-08T02:16:39Z

‎QA

Lr：以“==Text Processing== ===LM development=== ====Domain specific LM==== * domain lm :* train some more LMs with Zhenlong (dianzishu sogou bbs chosen),put result on cvss...”为内容创建页面

2014-12-08T02:14:49Z

以“==Text Processing== ===LM development=== ====Domain specific LM==== * domain lm :* train some more LMs with Zhenlong (dianzishu sogou bbs chosen),put result on cvss...”为内容创建页面

新页面

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

====Domain specific LM====
* domain lm
:* train some more LMs with Zhenlong (dianzishu sogou bbs chosen),put result on cvss.
:* Sougou2T : kn-count.
:* lm v2.0 continue('''this week''')

* new dict.
:* Released vocab v2.0 (mainly done by Dongxu) to JieTong.

====tag LM====
* summary done
* need to do
:* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong (hold)
:* make a summary about tag-lm and '''journal paper'''(wxx and yuanb)('''this weeks''').
::* Reviewed papers and begin to write paper ('''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 started
:* Analysis the wiki infomation of category and link into jso done, knowledge vector build graph done.
:* begin to code for train
====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===
deatil:
====Spell mistake====
* retrain the ngram model('''caoli''')
====improve fuzzy match====
* add Synonyms similarity using MERT-4 method(hold)
====improve lucene search====
:* using MERT-4 method to get good value of multi-feature.like IDF,NER,baidu_weight,keyword etc.('''liurong this month''')
====Multi-Scene Recognition====
* done
====XiaoI framework====
* give a report about xiaoI framework
* new inter will install SEMPRE
====patent====
* done

←上一版本		2014年12月8日 (一) 08:43的版本
第1行：		第1行：
		+	==Speech Processing ==
		+	=== AM development ===
		+
		+	==== Environment ====
		+	* Already buy 3 760GPU
		+	* grid-9/12 760GPU crashed again; grid-11 shutdown automatically.
		+	* Change 760gpu card of grid-12 and grid-14(+).
		+
		+	==== Sparse DNN ====
		+	* Performance improvement found when pruned slightly
		+	* need retraining for unpruned one; training loss
		+	* details at http://liuc.cslt.org/pages/sparse.html
		+	* HOLD
		+
		+	==== RNN AM====
		+	* Initial nnet seems not very well, need to be pre-trained or test lower learn-rate.
		+	* For AURORA 4 1h/epoch, model train done.
		+	* Using AURORA 4 short-sentence with a smaller number of targets.(+)
		+	* Adjusting the learning rate.(+)
		+	* Trying toolkit of Microsoft.(+)
		+	* details at http://liuc.cslt.org/pages/rnnam.html
		+	* Reading papers
		+
		+	==== A new nnet training scheduler ====
		+	* Initial code done. No better than original one considering of taking much more iterations.
		+	* details at http://liuc.cslt.org/pages/nnet-sched.html
		+	* done.
		+
		+	====Drop out & Rectification & convolutive network====
		+
		+	* Drop out(+)
		+	:* AURORA4 dataset
		+
		+	:* Use different proportion of noise data to investigate the effect of xEnt and mpe and dropout
		+	:** Problem 1) The effect of dropout in different noise proportion;
		+	<pre>
		+	No. \| data & config \| test_clean_wv1 \| test_airport_wv1 \| test_babble_wv1 \| test_car_wv1 \|
		+	---------------------------------------------------------------------------------------------------
		+	1 \| clean-std \| 6.74 \| 28.77 \| 31.84 \| 14.24 \|
		+	---------------------------------------------------------------------------------------------------
		+	2 \| clean-dropout0.8 \| 6.78 \| 25.89 \| 26.45 \| 12.57 \|
		+	---------------------------------------------------------------------------------------------------
		+	3 \| noise-20%-std \| 6.76 \| 14.74 \| 14.32 \| 8.87 \|
		+	---------------------------------------------------------------------------------------------------
		+	4 \| noise-20%-dropout0.8 \| 7.01 \| 14.51 \| 13.61 \| 9.22 \|
		+	---------------------------------------------------------------------------------------------------
		+	5 \| noise-100%-std \| 9.03 \| 11.21 \| 11.44 \| 7.96 \|
		+	---------------------------------------------------------------------------------------------------
		+	6 \| noise-100%-dropout0.8\| 8.87 \| 11.58 \| 12.22 \| 8.38 \|
		+	---------------------------------------------------------------------------------------------------
		+	</pre>
		+	2) The effect of MPE in different noise proportion;
		+	3) The effect of MPE+dropout in different noise proportion.
		+	:**http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=261
		+
		+	:** Find and test unknown noise test-data.(++)
		+	:** Have done the droptout on normal trained XEnt NNET , eg wsj(learn-rate:1e-4/1e-5). Seems small learn-rate get the balance of accuracy and train-time.
		+
		+	* MaxOut(+)
		+	:* pretraining based maxout, can't use large learning-rate.
		+	:** Select units in Groupsize interval, but need low learn-rate
		+
		+	* SoftMaxout
		+
		+	* P-norm
		+	:* Need to solve the too small learning-rate problem
		+	:** Add one normalization layer after the pnorm-layer
		+
		+	* Convolutive network (+)
		+	:* AURORA 4
		+	--------------------------------------------------------------------------------------------------------------------------
		+	nonlda \| %WER \|Dnn l-u \| pool size-step\| cnn dim-step-num \| cnn_init_opts
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_std \| 5.73 \| 4 - 1200 \| 3 - 3 \| 8-1-128 512-128-256 \|--patch-dim1 8
		+	\| \| \| \| \|--input_dim~patch-dim1
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_cnnunit_384 \| 5.85 \| 4 - 1200 \| 3 - 3 \| 8-1-128 512-128-384 \|--patch-dim1 8
		+	\| \| \| \| \|--num-filters2 384
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_patchdim1_5 \| 5.92 \| 4 - 1200 \| 3 - 3 \| 5-1-128 512-128-256 \|--patch-dim1 5
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_patchdim1_11 \| 6.05 \| 4 - 1200 \| 3 - 3 \| 11-1-128 512-128-256 \|--patch-dim1 11
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_delta_1 \| 5.98 \| 4 - 1200 \| 3 - 3 \| 8-1-128 512-128-256 \|--patch-dim1 8
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_delta_2 \| 6.05 \| 4 - 1200 \| 3 - 3 \| 8-1-128 512-128-256 \|--patch-dim1 8
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_layer_3 \| 6.00 \| 4 - 1200 \| 3 - 3 3 - 1 \| 8-1-128 512-128-256 768-256-512 \|--patch-dim1 8
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_layer_3_2 \| 5.85 \| 4 - 1200 \| 3 - 3 2 - 2 \| 8-1-128 512-128-256 768-256-512 \|--patch-dim1 8
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_layer_3_3 \| 5.73 \| 4 - 1200 \| 3 - 3 2 - 2 \| 8-1-128 512-128-256 512-256-512 \|--patch-dim1 8
		+	--------------------------------------------------------------------------------------------------------------------------
		+	cnn_layer_3_4 \| 5.96 \| 4 - 1200 \| 3 - 3 2 - 2 \| 8-1-128 512-128-256 256-256-512 \|--patch-dim1 8
		+	--------------------------------------------------------------------------------------------------------------------------
		+
		+	====DAE(Deep Atuo-Encode)====
		+	(1) train_clean
		+	drop-retention/testcase(WER)\| test_clean_wv1 \| test_airport_wv1 \| test_babble_wv1 \| test_car_wv1
		+	---------------------------------------------------------------------------------------------------------
		+	std-xEnt-sigmoid-baseline\| 6.04 \| 29.91 \| 27.76 \| 16.37
		+	---------------------------------------------------------------------------------------------------------
		+	std+dae_cmvn_noFT_2-1200 \| 7.10 \| 15.33 \| 16.58 \| 9.23
		+	---------------------------------------------------------------------------------------------------------
		+	std+dae_cmvn_splice5_2-100 \| 8.19 \| 15.21 \| 15.25 \| 9.31
		+	---------------------------------------------------------------------------------------------------------
		+
		+	:* 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
		+
		+	====Denoising & Farfield ASR====
		+	* ICASSP paper submitted.
		+	* HOLD
		+
		+	====VAD====
		+	* Harmonics and Teager energy features being investigation (++)
		+
		+	====Speech rate training====
		+	* Data ready on tencent set; some errors on speech rate dependent model. error fixed.
		+	* Retrain new model(+)
		+
		+	====Scoring====
		+	* Timber Comparison done.
		+	* harmonics based timber comparison: frequency based feature is better. done
		+	* GMM based timber comparison is done. Similar to speaker recognition. done
		+	* TODO: Code checkin and '''technique report'''. done
		+
		+	====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===
		+	* Preparing GMM-based server.
		+	* EER ~ 4% (GMM-based system)--Text independent
		+	* EER ~ 6%(1s) / 0.5%(5s) (GMM-based system)--Text dependent
		+	* test different number of components; fast i-vector computing
		+
		+	===Language ID===
		+	* GMM-based language is ready.
		+	* Delivered to Jietong
		+	* Prepare the test-case
		+
		+	===Voice Conversion===
		+	* Yiye is reading materials(+)
		+
		+
	==Text Processing==		==Text Processing==
	===LM development===		===LM development===

@@ 第9行： / 第9行： @@
 *  new dict.
 :* Released vocab v2.0 (mainly done by Dongxu) to JieTong.
-;;* using minimum size segmentation and artificial add the long word(like 中华人民共和国)
+::* using minimum size segmentation and artificial add the long word(like 中华人民共和国)
 :* check the v2.0-dict with small data.

@@ 第9行： / 第9行： @@
 *  new dict.
 :* Released vocab v2.0 (mainly done by Dongxu) to JieTong.
-;;* some problem: using minimum size segmentation and artificial add the long word(like 中华人民共和国)
+;;* using minimum size segmentation and artificial add the long word(like 中华人民共和国)
 :* check the v2.0-dict with small data.

@@ 第4行： / 第4行： @@
 ====Domain specific LM====
 * domain lm
-:* Sougou2T : kn-count.
+:* Sougou2T : kn-count continue .
-:* lm v2.0 continue('''this week''')
+:* lm v2.0 set up('''this week''')
 *  new dict.

@@ 第60行： / 第60行： @@
 * done
 ====XiaoI framework====
-* give a report about xiaoI framework
+* ner from xiaoI
 * new inter will install SEMPRE
 ====patent====
 * done

@@ 第51行： / 第51行： @@
 deatil:
 ====Spell mistake====
-* retrain the ngram model('''caoli''')
+* add the xiaoI pingyin correct to framework.
 ====improve fuzzy match====
 * add Synonyms similarity using MERT-4 method(hold)
 ====improve lucene search====
 :* using MERT-4 method to get good value of multi-feature.like IDF,NER,baidu_weight,keyword etc.('''liurong this month''')
 ====Multi-Scene Recognition====
 * done