2015年8月3日 (一) 02:44的版本 （查看源代码） Xingchao（讨论 | 贡献） ←上一编辑		2015年8月3日 (一) 07:24的版本 （查看源代码） Zxw（讨论 | 贡献） （→‎Speech Processing） 下一编辑→
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	+	*write code to tune learning rate
	==== Mic-Array ====		==== Mic-Array ====

---

2015年8月3日 (一) 07:24的版本

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

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

• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261

Speaker ID

• DNN-based sid --Lantian

• http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327

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.

Text Intuitive Idea

Trace Learning

• (Hold)

Match RNN

• (Hold)

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