“ASR:2015-10-19”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（→‎Speech Processing）
（→‎Speech Processing）
第7行： 第7行：
 
*train monophone RNN --zhiyuan
 
*train monophone RNN --zhiyuan
 
:* end to end MPE
 
:* end to end MPE
 +
:*http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=446
 
* train RNN MPE using large dataset--mengyuan
 
* train RNN MPE using large dataset--mengyuan
 
:* better mpe result observed ,unknown errors in previous lstm mpe compiling kaldi
 
:* better mpe result observed ,unknown errors in previous lstm mpe compiling kaldi
第54行： 第55行：
 
:* 7*2048 8k 1400h tdnn training Xent done
 
:* 7*2048 8k 1400h tdnn training Xent done
 
:* nnet3 mpe code is under investigation
 
:* nnet3 mpe code is under investigation
 +
:*http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=472
  
 
===multi-task===
 
===multi-task===

2015年10月26日 (一) 07:29的版本

Speech Processing

AM development

Environment

RNN AM

  • train monophone RNN --zhiyuan
  • train RNN MPE using large dataset--mengyuan

Learning rate tunning

  • sequence training -Xiangyu

Mic-Array

  • hold
  • compute EER with kaldi

Data selection unsupervised learning

  • hold
  • acoustic feature based submodular using Pingan dataset --zhiyong
  • write code to speed up --zhiyong
  • curriculum learning --zhiyong

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

  • hold
  • RNN-DAE has worse performance than DNN-DAE because training dataset is small
  • extract real room impulse to generate WSJ reverberation data, and then train RNN-DAE

Ivector&Dvector based ASR

  • learning from ivector --Lantian
  • CNN ivector learning
  • DNN ivector learning
  • binary ivector
  • metric learning


language vector

  • write a paper--zhiyuan
  • hold
  • language vector is added to multi hidden layers--zhiyuan
  • RNN language vector
  • hold

multi-GPU

  • multi-stream training --Sheng Su
  • the problem of more than two GPUs is solved
  • kaldi-nnet3 --Xuewei

multi-task

  • test according to selt-information neural structure learning --mengyuan
  • write code done
  • no significant performance improvement observed
  • speech rate learning --xiangyu

Text Processing

RNN LM

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

Neural Based Document Classification

  • (hold)

RNN Rank Task

  • Test.
  • Paper: RNN Rank Net.
  • (hold)
  • Output rank information.

Graph RNN

  • Entity path embeded to entity.
  • (hold)

RNN Word Segment

  • Set bound to word segment.
  • (hold)

Seq to Seq(09-15)

  • Review papers.
  • Reproduce baseline. (08-03 <--> 08-17)

Order representation

  • Nested Dropout
  • semi-linear --> neural based auto-encoder.
  • modify the objective function(hold)

Balance Representation

  • Find error signal

Recommendation

  • Reproduce baseline.
  • LDA matrix dissovle.
  • LDA (Text classification & Recommendation System) --> AAAI

RNN based QA

  • Read Source Code.
  • Attention based QA.
  • Coding.

RNN Poem Process

  • Seq based BP.
  • (hold)

Text Group Intern Project

Buddhist Process

  • (hold)

RNN Poem Process

  • Done by Haichao yu & Chaoyuan zuo Mentor : Tianyi Luo.

RNN Document Vector

  • (hold)

Image Baseline

  • Demo Release.
  • Paper Report.
  • Read CNN Paper.

Text Intuitive Idea

Trace Learning

  • (Hold)

Match RNN

  • (Hold)

financial group

model research

  • RNN
  • online model, update everyday
  • modify cost function and learning method
  • add more feature

rule combination

  • GA method to optimize the model

basic rule

  • classical tenth model

multiple-factor

  • add more factor
  • use sparse model

display

  • bug fixed
  • buy rule fixed

data

  • data api
  • download the future data and factor data
取自“http://cslt.org/mediawiki/index.php?title=ASR:2015-10-19&oldid=17334”