“ASR:2015-01-05”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（以“==Text Processing== ===LM development=== ====Domain specific LM==== * LM2.0 :* mix the sougou2T-lm,kn-discount continue :* train a large lm using 25w-dict.(hanzheng...”为内容创建页面）
 
 
（相同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 ====
 +
* May gpu760 of grid-14 be something wrong. To be exchanged.
 +
 +
==== Sparse DNN ====
 +
* details at http://liuc.cslt.org/pages/sparse.html
 +
* need to test clean data
 +
* MPE training to be continue
 +
 +
==== RNN AM====
 +
* Trying toolkit of Microsoft.(+)
 +
* details at http://liuc.cslt.org/pages/rnnam.html
 +
 +
====Dropout & Maxout & retifier ====
 +
* Drop out
 +
:* Change the test data to more noisy data, to verify the effectiveness of dropout.
 +
 +
* 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)====
 +
:* 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
 +
:** Technical report to draft, Mengyuan Zhao and Zhiyong Zhang.
 +
:* To test real enviroment echo.
 +
 +
====VAD====
 +
* Harmonics and Teager energy features done.
 +
* Model to be trained.
 +
 +
====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(+)
 +
 +
 
==Text Processing==
 
==Text Processing==
 
===LM development===
 
===LM development===

2015年1月9日 (五) 10:05的最后版本

Speech Processing

AM development

Environment

  • May gpu760 of grid-14 be something wrong. To be exchanged.

Sparse DNN

RNN AM

Dropout & Maxout & retifier

  • Drop out
  • Change the test data to more noisy data, to verify the effectiveness of dropout.
  • 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)

DNN-DAE(Deep Atuo-Encode-DNN)

VAD

  • Harmonics and Teager energy features done.
  • Model to be trained.

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

Neural network visulization

Speaker ID

Language ID

Voice Conversion

  • Yiye is reading materials(+)


Text Processing

LM development

Domain specific LM

  • LM2.0
  • 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
  • paper submit this week.

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

  • 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.

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 ..

XiaoI framework

  • context in xiaoI
  • make a report

query normalization

  • using NER to normalize the word
  • new inter will install SEMPRE
取自“http://index.cslt.org/mediawiki/index.php?title=ASR:2015-01-05&oldid=13442”