“ASR:2014-12-29”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
Domain specific LM
 
(某位用户的一个中间修订版本未显示)
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128行:
 
====improve lucene search====
 
====improve lucene search====
 
:* add more feature to improve search.
 
:* add more feature to improve search.
::*  
+
::* POS, NER ,tf ,idf ..
 +
 
 
====XiaoI framework====
 
====XiaoI framework====
 
*  context in xiaoI
 
*  context in xiaoI

2014年12月29日 (一) 08:48的最后版本

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

RNN AM

A new nnet training scheduler

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)

DAE(Deep Atuo-Encode-DNN)

VAD

  • Harmonics and Teager energy features being investigation (++)

Speech rate training

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

Voice Conversion

  • Yiye is reading materials(+)


Text Processing

LM development

Domain specific LM

  • LM2.0
  • data check for lexicon(jietong)
  • merge lm with NAME POI etc.(hanzhenglong/wxx)
  • 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
  • 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.[1]
  • 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)[2]

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.
  • POS, NER ,tf ,idf ..

XiaoI framework

  • context in xiaoI

query normalization

  • using NER to normalize the word
  • new inter will install SEMPRE