“ASR:2015-07-27”版本间的差异
来自cslt Wiki
（→Text Processing） |
（→Speech Processing） |
||
| （2位用户的9个中间修订版本未显示） | |||
| 第3行： | 第3行： | ||
==== Environment ==== | ==== Environment ==== | ||
| − | * grid-14 is on | + | * grid-14 is on repairation |
* prepare to buy a server | * prepare to buy a server | ||
| 第11行： | 第11行： | ||
*morpheme RNN --zhiyuan | *morpheme RNN --zhiyuan | ||
*train using 1400h large dataset--mengyuan | *train using 1400h large dataset--mengyuan | ||
| + | *write code to tune learning rate--mengyuan | ||
==== Mic-Array ==== | ==== Mic-Array ==== | ||
| 第26行： | 第27行： | ||
* deliver to mengyuan | * deliver to mengyuan | ||
:* 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=== | ===Speaker ID=== | ||
* DNN-based sid --Lantian | * DNN-based sid --Lantian | ||
| 第39行： | 第40行： | ||
:*--hold | :*--hold | ||
| − | === | + | ===language vector=== |
* hold | * hold | ||
| − | |||
| − | |||
| − | |||
| − | |||
* train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan | * train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan | ||
:* hold | :* hold | ||
* write a paper--zhiyuan | * write a paper--zhiyuan | ||
| + | * RNN language vector | ||
| + | * train as a paper--xuewei | ||
===rectifier=== | ===rectifier=== | ||
* hold | * hold | ||
| − | * rectifier RNN | + | * rectifier RNN --zhiyuan |
===monophone=== | ===monophone=== | ||
| + | * hold | ||
* triphone is tranfered to monophone | * triphone is tranfered to monophone | ||
| − | |||
| − | |||
| − | |||
==Text Processing== | ==Text Processing== | ||
| 第66行： | 第63行： | ||
====Neural Based Document Classification==== | ====Neural Based Document Classification==== | ||
| + | * (hold) | ||
| + | |||
| + | ====RNN Rank Task==== | ||
* (hold) | * (hold) | ||
====RNN Word Segment==== | ====RNN Word Segment==== | ||
* (hold) | * (hold) | ||
| + | |||
| + | ====Seq to Seq(09-15)==== | ||
| + | * Review papers. | ||
| + | * Reproduce baseline. (08-03) | ||
====Order representation ==== | ====Order representation ==== | ||
| 第89行： | 第93行： | ||
====RNN based QA==== | ====RNN based QA==== | ||
*Read Source Code. | *Read Source Code. | ||
| − | |||
| − | |||
| − | |||
| − | |||
===Text Group Intern Project=== | ===Text Group Intern Project=== | ||
| 第106行： | 第106行： | ||
:*Paper Report. | :*Paper Report. | ||
*Read CNN Paper. | *Read CNN Paper. | ||
| + | |||
| + | =financial group= | ||
| + | ===world quant=== | ||
| + | * websim(done) | ||
| + | :* learn the websim and test several alpha | ||
| + | :* submit the alpha | ||
| + | |||
| + | ===tonglian platform=== | ||
| + | * learn the platform | ||
| + | :* test the alpha in tonglian platform | ||
| + | :* verify the Theano in tonglian | ||
| + | |||
| + | ===strategy=== | ||
| + | * ml strategy | ||
| + | :* ml method | ||
| + | * optimize the strategy | ||
| + | :* optimize the model | ||
| + | * classical strategy | ||
| + | :* | ||
2015年7月27日 (一) 06:43的最后版本
目录
- 1 Speech Processing
- 2 Text Processing
- 3 financial group
Speech Processing
AM development
Environment
- grid-14 is on repairation
- prepare to buy a server
RNN AM
- hold
- morpheme RNN --zhiyuan
- train using 1400h large dataset--mengyuan
- write code to tune learning rate--mengyuan
Mic-Array
- hold
- compute EER with kaldi
====Data selection unsupervised learning
- hold
- acoustic feature based submodular using Pinan dataset --zhiyong
- write code to speed up --zhiyong
RNN-DAE(Deep based Auto-Encode-RNN)
- hold
- deliver to mengyuan
Speaker ID
- DNN-based sid --Lantian
Ivector&Dvector based ASR
- hold --Tian Lan
- Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
- dark-konowlege using i-vector
- train on wsj(testbase dev93+evl92)
- --hold
language vector
- hold
- train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan
- hold
- write a paper--zhiyuan
- RNN language vector
- train as a paper--xuewei
rectifier
- hold
- rectifier RNN --zhiyuan
monophone
- hold
- triphone is tranfered to monophone
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
- (hold)
RNN Word Segment
- (hold)
Seq to Seq(09-15)
- Review papers.
- Reproduce baseline. (08-03)
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
DSSM based QA
- Demo Release.(English done.)
- Chinese Model start.
RNN based QA
- Read Source Code.
Text Group Intern Project
Buddhist Process
(hold)
RNN Poem Process
- Read Paper & Source Code.
RNN Document Vector
(hold)
Image Baseline
- Demo Release.
- Paper Report.
- Read CNN Paper.
financial group
world quant
- websim(done)
- learn the websim and test several alpha
- submit the alpha
tonglian platform
- learn the platform
- test the alpha in tonglian platform
- verify the Theano in tonglian
strategy
- ml strategy
- ml method
- optimize the strategy
- optimize the model
- classical strategy
