From cslt Wiki
Jump to: navigation, search

Speech Processing

AM development


  • May gpu760 of grid-14 be something wrong. To be exchanged.
  • grid-2 can not be booted
  • grid-10 should replac the CPU fan.

Sparse DNN


Dropout & Maxout & retifier

  • Drop out
  • 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)
  • 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)

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


  • Harmonics and Teager energy features done.
  • Frame energy Model training done.
  • Other features model to be train.

Speech rate training


  • 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
  • HOLD

Text Processing

LM development

Domain specific LM

  • LM2.1
  • mix the sougou2T-lm,kn-discount continue
  • train a large lm using 25w-dict.(hanzhenglong/wxx)
  • data pre-processing("this week")
  • new dict.
  • dongxu help zhenglong with large dictionary.

tag LM

  • Tag Lm
  • tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong ("this month")
  • paper
  • paper submit this week.
  • similar word extension in FST
  • find similarity word using word2vec,word vector is training.
  • set the weight for word


  • 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)


W2V based doc classification

  • data prepare.

Knowledge vector

  • Knowledge vector
  • Make a proper test set.
  • Modify the object function and training process.


Character to word

  • Character to word conversion(hold)


  • v5.0 demo released
  • cut the dict and use new segment-tool


improve fuzzy match

  • add Synonyms similarity using MERT-4 method(hold)

improve lucene search

  • add more feature to improve search.
  • POS, NER ,tf ,idf ..

context framework

  • code for organization

query normalization

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