From cslt Wiki
Jump to: navigation, search

Speech Processing

AM development


  • May gpu760 of grid-14 has been repairing.
  • grid-11 often shutdown automatically, too slow computation speed.



  • XueWei is reading papers and preparing the technical report

Dropout & Maxout & rectifier

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

Convolutive network

  • Convolutive network(DAE)

DNN-DAE(Deep Auto-Encode-DNN)

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


  • DAE
  • HOLD
  • Technical report -- Shi Yin

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

Text Processing

LM development

Domain specific LM

  • LM2.X
  • mix the sougou2T-lm,kn-discount continue
  • train a large lm using 25w-dict.(hanzhenglong/wxx)
  • v2.0a adjust the weight and smaller weight of transportation is better.(done)
  • v2.0b add the v1.0 vocab(this week)
  • v2.0c filter the useless word.(next week)
  • set the test set for new word (hold)

tag LM

  • Tag Lm
  • code is given to jietong .
  • similar word extension in FST
  • write a draft of a paper
  • result [1]


  • 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

  • run the big data
  • prepare the paper.

Character to word

  • Character to word conversion(hold)


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

Sparse NN in NLP

  • write a technical report(Wednesday) and make a repoert.


improve fuzzy match

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

improve lucene search

  • add more feature to improve search.
  • POS, NER ,tf ,idf
  • result:P@1: 0.68734335-->0.7763158P@5: 0.80325814-->0.8383459 [2]
  • Optimize the code about extracting features and reranking and commit to Rong Liu to check in.
  • using sentence vector, it doesn't work.

online learning

  • a simple edition about online learning part about QA.

context framework

  • code for organization
  • change to knowledge graph,and learn the D2R tool and JENA

query normalization

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