“ASR:2015-09-21”版本间的差异
来自cslt Wiki
（以“==Speech Processing == === AM development === ==== Environment ==== * grid-12 GPU is transferred to grid-18 * buy a 970 GPU ==== RNN AM==== *train monophone RNN --...”为内容创建页面） |
（→Speech Processing） |
||
| （2位用户的4个中间修订版本未显示） | |||
| 第4行： | 第4行： | ||
==== Environment ==== | ==== Environment ==== | ||
* grid-12 GPU is transferred to grid-18 | * grid-12 GPU is transferred to grid-18 | ||
| − | * | + | * grid-14 is unstable |
==== RNN AM==== | ==== RNN AM==== | ||
*train monophone RNN --zhiyuan | *train monophone RNN --zhiyuan | ||
:* decode using 5-gram | :* decode using 5-gram | ||
| − | :* the train method of batch | + | :* the train method of batch |
| − | * train using large dataset--mengyuan | + | :* test using another test set |
| − | * | + | * train RNN MPE using large dataset--mengyuan |
| − | + | :* diverge problem | |
| + | |||
| + | ====Learning rate tunning==== | ||
| + | * has completed Nestrov/Adagrad/Adagrad-max--zhiyong | ||
:* has unstable phenomenon | :* has unstable phenomenon | ||
| − | + | * completed adam,adadeta,adam-max --Xiangyu,Zhiyong | |
| − | + | * reproduce PSO --Xiangyu | |
| + | * sequence training -Xiangyu | ||
==== Mic-Array ==== | ==== Mic-Array ==== | ||
| 第21行： | 第25行： | ||
* compute EER with kaldi | * compute EER with kaldi | ||
| − | ====Data selection unsupervised learning | + | ====Data selection unsupervised learning==== |
* hold | * hold | ||
* acoustic feature based submodular using Pingan dataset --zhiyong | * acoustic feature based submodular using Pingan dataset --zhiyong | ||
* write code to speed up --zhiyong | * write code to speed up --zhiyong | ||
| + | * curriculum learning --zhiyong | ||
====RNN-DAE(Deep based Auto-Encode-RNN)==== | ====RNN-DAE(Deep based Auto-Encode-RNN)==== | ||
| 第42行： | 第47行： | ||
===language vector=== | ===language vector=== | ||
* hold | * hold | ||
| − | |||
* write a paper--zhiyuan | * write a paper--zhiyuan | ||
* RNN language vector | * RNN language vector | ||
| − | :* hold | + | :* hold |
===multi-GPU==== | ===multi-GPU==== | ||
* multi-stream training --Sheng Su | * multi-stream training --Sheng Su | ||
:* two GPUs work well, but four GPUs divergent | :* two GPUs work well, but four GPUs divergent | ||
| − | * solve the problem of buffer-- | + | * solve the problem of buffer-- Sheng Su |
| − | ===Neutral picture style transfer== | + | ===Neutral picture style transfer== |
| + | *hold | ||
* reproduced the result of the paper "A neutral algorithm of artistic style" --Zhiyuan, Xuewei | * reproduced the result of the paper "A neutral algorithm of artistic style" --Zhiyuan, Xuewei | ||
* while subject to the GPU's memory, limited to inception net with sgd optimizer (VGG network with the default L-BFGS optimizer consumes very much memory, which is better) | * while subject to the GPU's memory, limited to inception net with sgd optimizer (VGG network with the default L-BFGS optimizer consumes very much memory, which is better) | ||
| + | |||
| + | ===Multi-task learning=== | ||
| + | * train model using speech rate --xiangyu | ||
| + | * speech recognition plus speaker reconition --xiangyu,lantian,zhiyuan | ||
==Text Processing== | ==Text Processing== | ||
2015年9月21日 (一) 09:00的最后版本
目录
- 1 Speech Processing
- 2 =Neutral picture style transfer
- 3 Text Processing
- 4 financial group
Speech Processing
AM development
Environment
- grid-12 GPU is transferred to grid-18
- grid-14 is unstable
RNN AM
- train monophone RNN --zhiyuan
- decode using 5-gram
- the train method of batch
- test using another test set
- train RNN MPE using large dataset--mengyuan
- diverge problem
Learning rate tunning
- has completed Nestrov/Adagrad/Adagrad-max--zhiyong
- has unstable phenomenon
- completed adam,adadeta,adam-max --Xiangyu,Zhiyong
- reproduce PSO --Xiangyu
- 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)
- 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
- Cluster the speakers to speaker-cluster
- hold
- dark knowledge
- has much worse performance than baseline (EER: base 29% dark knowledge 48%)
- RNN ivector
- hold
- binary ivector done
- metric learning
language vector
- hold
- write a paper--zhiyuan
- RNN language vector
- hold
multi-GPU=
- multi-stream training --Sheng Su
- two GPUs work well, but four GPUs divergent
- solve the problem of buffer-- Sheng Su
=Neutral picture style transfer
- hold
- reproduced the result of the paper "A neutral algorithm of artistic style" --Zhiyuan, Xuewei
- while subject to the GPU's memory, limited to inception net with sgd optimizer (VGG network with the default L-BFGS optimizer consumes very much memory, which is better)
Multi-task learning
- train model using speech rate --xiangyu
- speech recognition plus speaker reconition --xiangyu,lantian,zhiyuan
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
