ASR:2015-03-30

Speech Processing

AM development

Environment

• grid-11 often shut down automatically, too slow computation speed.
• GPU has being repired.--Xuewei

RNN AM

• details at http://liuc.cslt.org/pages/rnnam.html
• tuning parameters on monophone NN

Mic-Array

• investigate alpha parameter in time domian and frquency domain

Dropout & Maxout & rectifier

• HOLD
• Need to solve the too small learning-rate problem
• 20h small scale sparse dnn with rectifier. --Mengyuan
• 20h small scale sparse dnn with Maxout/rectifier based on weight-magnitude-pruning. --Mengyuan Zhao

Convolutive network

• HOLD

• CNN + DNN feature fusion
• reproduce experiments -- Yiye

RNN-DAE(Deep based Auto-Encode-RNN)

• HOLD -Zhiyong
• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261

Speech rate training

• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=268
• Technical report HOLD.-- Xiangyu Zeng, Shi Yin
• Paper for NCMMSC done

Neural network visulization

• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=324
• Technical report done --Mian Wang.

Speaker ID

• DNN-based sid --Yiye
• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327

Ivector based ASR

• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=340
• Ivector dimention is smaller, performance is better
• Augument to hidden layer is better than input layer
• write paper for interspeech -- Xuewei

Text Processing

tag LM

• similar word extension in FST

• check the formula using Bays and experiment

RNN LM

• rnn

• code the character-lm using Theano

• lstm+rnn

• check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)

W2V based doc classification

• data prepare.

Translation

• v5.0 demo released

• cut the dict and use new segment-tool

Sparse NN in NLP

• prepare the ACL

• check the code to find the problem .
• increase the dimension
• use different test set,but the result is not good.

online learning

• data is ready.prepare the ACL paper

• prepare sougouQ data and test it using current online learning method
• baseline is not normal.