“ASR:2015-08-24”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
financial group
Lr讨论 | 贡献
financial group
 
(2位用户的2个中间修订版本未显示)
第3行: 第3行:
  
 
==== Environment ====
 
==== Environment ====
* grid-14 is on repairation
+
 
* prepare to buy a server
+
  
 
==== RNN AM====
 
==== RNN AM====
第25行: 第24行:
 
* deliver to mengyuan, xuewei
 
* deliver to mengyuan, xuewei
 
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261
 
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261
 
===Speaker ID=== 
 
*  DNN-based sid --Lantian
 
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327
 
 
   
 
   
  
===Ivector&Dvector based ASR===
+
===Ivector&Dvector based ASR===  
* hold --Tian Lan
+
 
* Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
 
* Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
 +
:*hold
 
* dark-konowlege using i-vector
 
* dark-konowlege using i-vector
* train on wsj(testbase dev93+evl92)
+
* RNN ivector
:*--hold
+
* binary ivector
  
 
===language vector===
 
===language vector===
第43行: 第38行:
 
:* hold
 
:* hold
 
* write a paper--zhiyuan
 
* write a paper--zhiyuan
 +
:*hold
 
* RNN language vector
 
* RNN language vector
* train as a paper--xuewei
+
:* hold  
 
+
===rectifier===
+
* hold
+
* rectifier RNN --zhiyuan
+
:* hold
+
  
  
第129行: 第120行:
 
* RNN
 
* RNN
 
:* online model, update everyday
 
:* online model, update everyday
 +
:* modify cost function and learning method
 
:* add more feature
 
:* add more feature
 
==rule combination==
 
==rule combination==
第138行: 第130行:
 
* bug fixed
 
* bug fixed
 
:* index calculation  
 
:* index calculation  
:*  
+
:* buy rule fixed
 +
* document
 
==data==
 
==data==
*
+
* data api
 +
* download data

2015年8月24日 (一) 08:01的最后版本

Speech Processing

AM development

Environment

RNN AM

  • train monophone RNN --zhiyuan
  • train using large dataset--mengyuan
  • write code to tune learning rate--zhiyong

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


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

  • hold
  • deliver to mengyuan, xuewei


Ivector&Dvector based ASR

  • Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
  • hold
  • dark-konowlege using i-vector
  • RNN ivector
  • binary ivector

language vector

  • hold
  • train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan
  • hold
  • write a paper--zhiyuan
  • hold
  • RNN language vector
  • hold


multi-GPU=

  • multi-stream training --Sheng Su

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

  • rule analysis

basic rule

  • classical tenth model

display

  • bug fixed
  • index calculation
  • buy rule fixed
  • document

data

  • data api
  • download data