“ASR:2015-08-17”版本间的差异
来自cslt Wiki
（以“==Speech Processing == === AM development === ==== Environment ==== * grid-14 is on repairation * prepare to buy a server ==== RNN AM==== *hold *train morpheme RN...”为内容创建页面） |
（→Text Processing） |
||
| 第81行： | 第81行： | ||
====Seq to Seq(09-15)==== | ====Seq to Seq(09-15)==== | ||
* Review papers. | * Review papers. | ||
| − | * Reproduce baseline. (08-03) | + | * Reproduce baseline. (08-03 <--> 08-17) |
====Order representation ==== | ====Order representation ==== | ||
| 第87行： | 第87行： | ||
:*semi-linear --> neural based auto-encoder. | :*semi-linear --> neural based auto-encoder. | ||
* modify the objective function(hold) | * modify the objective function(hold) | ||
| + | |||
====Balance Representation==== | ====Balance Representation==== | ||
* Find error signal | * Find error signal | ||
| 第101行： | 第102行： | ||
====RNN Poem Process==== | ====RNN Poem Process==== | ||
| − | *Seq based BP. | + | :*Seq based BP. |
| + | *(hold) | ||
===Text Group Intern Project=== | ===Text Group Intern Project=== | ||
====Buddhist Process==== | ====Buddhist Process==== | ||
| − | (hold) | + | :*(hold) |
====RNN Poem Process==== | ====RNN Poem Process==== | ||
| 第111行： | 第113行： | ||
====RNN Document Vector==== | ====RNN Document Vector==== | ||
| − | (hold) | + | :*(hold) |
====Image Baseline==== | ====Image Baseline==== | ||
2015年8月17日 (一) 02:56的版本
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
- train morpheme RNN --zhiyuan
- train using 1400h 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
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--zhiyong
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
- Paper: RNN Rank Net.
- (hold)
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.
- (hold)
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
tonglian platform
- learn the platform
- arma,ar,boosting tree is done
strategy
- rule optimize model
- Adaboost method
- technology index
- survey the current technology index
- NN
- RNN model using Theano
display platform
- set up the test platform in our grid
