ASR:2014-12-15 - 版本历史

Lr：/* Knowledge vector */

2014-12-22T06:13:04Z

‎Knowledge vector

Lr：/* QA */

2014-12-22T06:12:36Z

‎QA

Lr：/* Knowledge vector */

2014-12-22T05:49:59Z

‎Knowledge vector

Lr：/* Text Processing */

2014-12-22T05:49:34Z

‎Text Processing

Lr：/* QA */

2014-12-15T11:38:31Z

‎QA

Lr：/* QA */

2014-12-15T11:38:22Z

‎QA

Lr：/* Text Processing */

2014-12-15T11:37:50Z

‎Text Processing

2014年12月15日 (一) 08:26 Zhangzy

2014-12-15T08:26:15Z

Zhangzy：以“==Speech Processing == === AM development === ==== Environment ==== * Already buy 3 760GPU * grid-9/12 760GPU crashed again; grid-11 shutdown automatically. * Chang...”为内容创建页面

2014-12-15T08:22:27Z

以“==Speech Processing == === AM development === ==== Environment ==== * Already buy 3 760GPU * grid-9/12 760GPU crashed again; grid-11 shutdown automatically. * Chang...”为内容创建页面

新页面

==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(+).
* First down-frequency of gpu760.

==== Sparse DNN ====
* Performance improvement found when pruned slightly
* need retraining for unpruned one; training loss
* details at http://liuc.cslt.org/pages/sparse.html

==== 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
* Test on 4000h dataset.

====Dropout & Maxout & Convolutive network====

* Drop out(+)

:* 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;
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
:* Conclusion
Dropout is effective for minority.

:** Find and test unknown noise test-data.(++)

* MaxOut
:* Pretraining based maxout, can't use large learning-rate.

* 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(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==
===LM development===

====Domain specific LM====
* domain lm
:* Sougou2T : kn-count continue .
:* lm v2.0 set up('''this week''')

* 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)
:* check the v2.0-dict with small data.

====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====
* 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''')
:* now test the performance.
====Multi-Scene Recognition====
* done
====XiaoI framework====
* ner from xiaoI
* new inter will install SEMPRE

====patent====
* done

@@ 第151行： / 第151行： @@
 :* Finish the baseline and compared with simple factorization method based on co-occurrence.
 :* Visualization of knowledge vector[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Shades_of_color.pdf]
 ====relation====

@@ 第168行： / 第168行： @@
 * add Synonyms similarity using MERT-4 method(hold)
 ====improve lucene search====
-:* mutli query's performance improve from 66.228 to 68.672. detail:[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Improved_search_method_by_rewrited_query]
+* domain keyword to improve search in lucene using mert
-:* check the MERT problem that doesn't mach the qa
+:* keyword in sentence,like frequency ,position.
 ====XiaoI framework====
-* ner from xiaoI done
+* context in QA
 ====query normalization====
 * using NER to normalize the word
-−
+*
 * new inter will install SEMPRE

@@ 第146行： / 第146行： @@
   Factorization:      0.698714                          0.747226
   Baseline:           0.721214                          0.778838
       testset: 70 couples (7 data scored 0, 2 data scored 1, 5 data scored 2, 8 data scored 3)
   Baseline:(category) 0.523433
@@ 第152行： / 第151行： @@
 :* Finish the baseline and compared with simple factorization method based on co-occurrence.
 :* Visualization of knowledge vector[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:Shades_of_color.pdf]
 ====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]

←上一版本		2014年12月15日 (一) 11:38的版本
第165行：		第165行：

	* new inter will install SEMPRE		* new inter will install SEMPRE
−
−	~~====patent====~~
−	* done

@@ 第154行： / 第154行： @@
 ===QA===
 ====improve fuzzy match====
 * add Synonyms similarity using MERT-4 method(hold)
@@ 第161行： / 第159行： @@
 :* mutli query's performance improve from 66.228 to 68.672. detail:[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Improved_search_method_by_rewrited_query]
 :* check the MERT problem that doesn't mach the qa
 ====XiaoI framework====
 * ner from xiaoI done

@@ 第114行： / 第114行： @@
 * domain lm
 :* Sougou2T : kn-count continue .
-*  new dict.
+*  lm v2.0.
 ====tag LM====
-* summary done
+* paper(two week)
-* need to do
+:* add more related work in introduction and rich the paper
-:* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong (hold)
-::* paper done,begin to modify .
 ====RNN LM====
@@ 第138行： / 第137行： @@
 * Non-linear inter-language transform: English-Spanish-Czch: wv model training done, transform model on investigation
 ====Knowledge vector====
-* Knowledge vector started
+* baseline
-:* code done,to test the baseline with a task.
+:* Debug the training part and add normalization, result in cvss[326].
-:* problem with weight.
+::*
 ====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]

@@ 第95行： / 第95行： @@
 * EER ~ 6%(1s) / 0.5%(5s) (GMM-based system)--Text dependent
 * test different number of components; fast i-vector computing
 ===Language ID===