ASR:2015-12-14

Speech Processing

AM development

End-to-End

• monophone ASR --Zhiyuan

• MPE
• CTC/nnet3/Kaldi

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
• Deep speaker embedding tasks

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

• language vector into multiple layers --Zhiyuan

• a Chinese paper

• speech rate into multiple layers --Zhiyuan

• verify the code for extra input(s) into DNN

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

• RNN AM training on big dataset --mengyuan

• fix decode bug
• nnet3 lstm & blstm training on sinovoice 120h dataset, using KALDI's default config. but result is worse than tdnn
• Test nnet3-MPE code from Xuewei on sinovoice 120h 16k dataset. Didn't observe performance improvement. There are still some bugs in the code.
• Run nnet3-ctc training on sinovoice 120h 16k dataset. Result looks ok, but worse than normal model.
• Start nnet3-ctc training on sinovoice 4000h 8k dataset.

• train mpe --Zhiyong,Xuewei

• train nnet3 mpe using data from Jietong--Xuewei
• modify code to print stats
• modify code to reduce memory

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

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