“ASR:2015-12-1”版本间的差异
来自cslt Wiki
（→Speech Processing） |
|||
| （3位用户的7个中间修订版本未显示） | |||
| 第1行： | 第1行： | ||
==Speech Processing == | ==Speech Processing == | ||
| + | |||
=== AM development === | === AM development === | ||
==== Environment ==== | ==== Environment ==== | ||
| − | ==== | + | ==== End-to-End ==== |
| − | * | + | *monophone ASR --Zhiyuan |
| − | :* | + | :* MPE |
| − | :* | + | :* CTC/nnet3/Kaldi |
| − | + | ||
| + | ==== conditioning learning ==== | ||
| + | * language vector into multiple layers --Zhiyuan | ||
| + | :* a Chinese paper | ||
| + | * speech rate into multiple layers --Zhiyuan | ||
| + | :*verify the code for extra input(s) into DNN | ||
====Adapative learning rate method==== | ====Adapative learning rate method==== | ||
* sequence training -Xiangyu | * sequence training -Xiangyu | ||
:* write a technique report | :* write a technique report | ||
| − | |||
==== Mic-Array ==== | ==== Mic-Array ==== | ||
| 第36行： | 第40行： | ||
* AutoEncoder + metric learning | * AutoEncoder + metric learning | ||
* binary ivector | * binary ivector | ||
| − | |||
| − | |||
===language vector=== | ===language vector=== | ||
| 第48行： | 第50行： | ||
* RNN language vector | * RNN language vector | ||
:*hold | :*hold | ||
| − | + | ||
===multi-GPU=== | ===multi-GPU=== | ||
| 第58行： | 第60行： | ||
:*http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=472 | :*http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=472 | ||
* train 7*2048 tdnn using 4000h data --Mengyuan | * train 7*2048 tdnn using 4000h data --Mengyuan | ||
| + | * 1700h+776h 16k nnet3 6*2000 training done, outperform 6776H_mpe model--Mengyuan | ||
| + | * wrote nnet3 biglm-decoder for sinovoice. | ||
* train mpe using wsj and aurara4 --Zhiyong,Xuewei | * train mpe using wsj and aurara4 --Zhiyong,Xuewei | ||
| + | * train nnet3 mpe using data from Jietong--Xuewei | ||
===multi-task=== | ===multi-task=== | ||
| 第69行： | 第74行： | ||
:* no significant performance improvement observed | :* no significant performance improvement observed | ||
:*http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=483 | :*http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=483 | ||
| − | : | + | : get results with extra input of speech rate info --Zhiyuan |
==Text Processing== | ==Text Processing== | ||
2015年12月7日 (一) 07:21的最后版本
目录
Speech Processing
AM development
Environment
End-to-End
- monophone ASR --Zhiyuan
- MPE
- CTC/nnet3/Kaldi
conditioning learning
- language vector into multiple layers --Zhiyuan
- a Chinese paper
- speech rate into multiple layers --Zhiyuan
- verify the code for extra input(s) into DNN
Adapative learning rate method
- sequence training -Xiangyu
- write a technique report
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
Speaker recognition
- DNN-ivector framework
- SUSR
- AutoEncoder + metric learning
- binary ivector
language vector
- write a paper--zhiyuan
- hold
- language vector is added to multi hidden layers--zhiyuan
- write code done
- check code
- http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=480
- RNN language vector
- hold
multi-GPU
- multi-stream training --Sheng Su
- write a technique report
- kaldi-nnet3 --Xuewei
- 7*2048 8k 1400h tdnn training Xent done
- 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
- train 7*2048 tdnn using 4000h data --Mengyuan
- 1700h+776h 16k nnet3 6*2000 training done, outperform 6776H_mpe model--Mengyuan
- wrote nnet3 biglm-decoder for sinovoice.
- train mpe using wsj and aurara4 --Zhiyong,Xuewei
- train nnet3 mpe using data from Jietong--Xuewei
multi-task
- test according to selt-information neural structure learning --mengyuan
- hold
- write code done
- no significant performance improvement observed
- speech rate learning --xiangyu
- hold
- no significant performance improvement observed
- http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=483
- get results with extra input of speech rate info --Zhiyuan
Text Processing
Work
RNN Poem Process
- Combine addition rhyme.
- Investigate new method.
Document Represent
- Code done. Wait some experiments result.
Seq to Seq
- Work on some tasks.
Order representation
- Code some idea.
Balance Representation
- Investigate some papers.
- Current solution : Use knowledge or large corpus's similar pair.
Hold
Neural Based Document Classification
RNN Rank Task
Graph RNN
- Entity path embeded to entity.
- (hold)
RNN Word Segment
- Set bound to word segment.
- (hold)
Recommendation
- Reproduce baseline.
- LDA matrix dissovle.
- LDA (Text classification & Recommendation System) --> AAAI
RNN based QA
- Read Source Code.
- Attention based QA.
- Coding.
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
