ASR:2015-03-23

From cslt Wiki
Jump to: navigation, search

Speech Processing

AM development

Environment

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

RNN AM


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)

Speech rate training

Neural network visulization

Speaker ID

Ivector based ASR

Text Processing

LM development

Domain specific LM

  • LM2.X
  • train a large lm using 25w-dict.(hanzhenglong/wxx)
  • v2.0c filter the useless Chinese word and add 500 English word. get a little promotion effect.

tag LM

  • Tag Lm(JT)
  • get new script from mx and test 1 tag lm
  • similar word extension in FST
  • experiment done
  • write the paper

RNN LM

  • rnn
  • the input and output is word embedding and add some token information like NER..
  • map the word to character and train the lm.
  • lstm+rnn
  • check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)

Word2Vector

W2V based doc classification

  • data prepare.(hold)

Knowledge vector

  • make a report on Monday

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.

QA

online learning

  • data is ready.prepare the ACL paper
  • prepare sougouQ data and test it using current online learning method

framework

  • extract the module
  • composite module
  • fix the bug

leftover problem

  • new inter will install SEMPRE