ASR:2015-01-05

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

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.

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