cslt Wiki - 用户贡献 [zh-cn]

Xi Ma 2015-08-17

2015-08-19T00:54:23Z

Mx：以“Last Week 1.Have a holiday in my home. This Week 1.Finish the experiment data for the similar-pair paper.”为内容创建页面

Last Week

1.Have a holiday in my home.

This Week

1.Finish the experiment data for the similar-pair paper.

2015-08-17

2015-08-19T00:48:36Z

Mx：

[[Tianyi Luo 2015-08-17]]

[[Mengyuan Zhao 2015-08-17]]

[[Chao Xing 2015-08-17]]

[[Sheng Su 2015-08-17]]

[[Zhiyuan Tang 2015-08-17]]

[[Xiaoxi Wang 2015-08-17]]

[[Xuewei Zhang2015-08-17]]

[[Zhiyong Zhang 2015-08-17]]

[[Rong Liu 2015-08-17]]

[[Ke Ning 2015-08-17]]

[[Xi Ma 2015-08-17]]

Xi Ma 15-07-21

2015-07-23T02:11:32Z

Mx：以“Last Week 1.Participate in the ChinaSIP2015. 2.Apply for the passport. This Week 1.Study the knowledge of quantitative investment. 2.Try some rules for the comp...”为内容创建页面

Last Week

1.Participate in the ChinaSIP2015.

2.Apply for the passport.

This Week

1.Study the knowledge of quantitative investment.

2.Try some rules for the competition "WorldQuant".

2015-07-20

2015-07-23T02:00:57Z

Mx：

[[Mengyuan Zhao 15-07-20]]

[[Zhiyuan Tang 15-07-20]]

[[Xuewei Zhang 15-07-20]]

[[Zhiyong Zhang 15-07-20]]

[[Lantian Li 15-07-21]]

[[Rong Liu 15-07-21]]

[[Yang Yu 15-07-21]]

[[Hui Tang 15-07-21]]

[[Xi Ma 15-07-21]]

Xi Ma 2015-07-14

2015-07-23T02:00:20Z

Mx：以“Last Week: 1.Prepare the presentation for the ChinaSIP2015. This Week: 1.Participate in the ChinaSIP2015.”为内容创建页面

Last Week:

1.Prepare the presentation for the ChinaSIP2015.

This Week:

1.Participate in the ChinaSIP2015.

2015-07-13

2015-07-23T01:57:01Z

Mx：

[[ Xiaoxi Wang 2015-07-13]]

[[Xuewei Zhang 2015-07-13]]

[[Chao Xing 2015-07-13]]

[[Zhiyuan Tang 2015-07-13]]

[[Zhiyong Zhang 2015-07-13]]

[[Tianyi Luo 2015-07-13]]

[[Mengyuan Zhao 2015-07-13]]

[[Lantian Li 2015-07-14]]

[[Xi Ma 2015-07-14]]

文件:Bi-month-mx.pdf

2015-07-10T05:35:22Z

Mx：

Bi-monthly-2015-06

2015-07-10T05:32:40Z

Mx：/* 个人报告 */

==打分总结==

小组打分：

{| class="wikitable"
!硬件环境 !! 实验室氛围 !!小组氛围 !! 工作量 !! 工作意义与创新
|-
|8 || 9 ||9 ||8 ||9
|-
|7 ||8 ||7 ||7 ||6
|-
|10 ||10 ||10 ||9 ||10
|-
|8 ||8 ||7 ||8 ||8
|-
|6 ||9 ||9 ||8 ||7
|-
|8 ||10 ||9 ||9 ||8
|-
|9 ||8 ||7 ||8 ||8
|-
|9 ||10 ||10 ||10 ||10
|-
|9 ||9 ||10 ||9 ||8
|-
|9 ||8 ||8 ||8 ||9
|-
|10 ||10 ||10 ||5 ||10
|-
|}

主要建议：

1. 组里建设需加强，早餐供应还应继续
2. 论文驱动明显
3. GPU不够

[[个人评分总结]]

==个人报告==
[[媒体文件:Bi-monthly_report-2015-06.pdf|王东]]

[[媒体文件:zhangzy_201504-06.pdf|张之勇]]

[[媒体文件:bi-monthly report Tang Zhiyuan.pdf|汤志远]]

[[媒体文件:Chaos.pdf|邢超]]

[[媒体文件:Tianyi's bi-monthly report.pdf|骆天一]]

[[媒体文件:Zmy_bimonth_20150626.pdf|赵梦原]]

[[媒体文件:150625-REPORT--LLT-.pdf|李蓝天]]

[[媒体文件:2015.04-06张雪薇季度总结.pdf|张雪薇]]

[[媒体文件:Bi-month-zdx.pdf|张东旭]]

[[媒体文件:Bi-month-mx.pdf|马习]]

Xi Ma 15-07-06

2015-07-07T02:17:46Z

Mx：以“Last Week 1.Design a web demo for the financial technical rules. 2.Learning the javascript toolkit of making chart. This Week 1.Preparing for the oral presention...”为内容创建页面

Last Week

1.Design a web demo for the financial technical rules.

2.Learning the javascript toolkit of making chart.

This Week

1.Preparing for the oral presention of ChinaSIP.

2.Trying stock practical manipulation in Shanghai Stock Exchange.

2015-07-06

2015-07-07T01:50:40Z

Mx：

[[Tianyi Luo 15-07-06]]

[[Chao Xing 15-07-06]]

[[Zhiyong Zhang 15-07-06]]

[[Mengyuan Zhao 15-07-06]]

[[Rong Liu 15-07-06]]

[[Xi Ma 15-07-06]]

Xi Ma 15-06-30

2015-07-07T01:50:03Z

Mx：以“Last Week 1.Learning the knowledge about the stock and finance. 2.Trying some basic technical rules of finance analysis. This Week 1.Design a web for the demo of...”为内容创建页面

Last Week

1.Learning the knowledge about the stock and finance.

2.Trying some basic technical rules of finance analysis.

This Week

1.Design a web for the demo of technical rules.

2015-06-29

2015-07-07T00:22:37Z

Mx：

[[Chao Xing 15-06-29]]

[[Tianyi Luo 15-06-29]]

[[Xiaoxi Wang 15-06-29]]

[[Zhiyong Zhang 15-06-29]]

[[Mengyuan Zhao 15-06-29]]

[[Xuewei Zhang 15-06-29]]

[[Zhiyuan Thang 15-06-29]]

[[Lantian Li 15-06-30]]

[[Xi Ma 15-06-30]]

Xi Ma 15-06-16

2015-06-18T07:04:53Z

Mx：以“Last Week: 1.Prepare the knowledge of programming language, data structure, algorithm and machine learning for the interview. This Week: 1.Prepare the knowledge o...”为内容创建页面

Last Week:

1.Prepare the knowledge of programming language, data structure, algorithm and machine learning for the interview.

This Week:

1.Prepare the knowledge of programming language, data structure, algorithm and machine learning for the interview.

2015-06-15

2015-06-18T06:57:33Z

Mx：

[[Zhiyong Zhang 15-06-15]]

[[Chao Xing 15-06-15]]

[[Mengyuan Zhao 15-06-15]]

[[Lantian Li 15-06-16]]

[[Zipeng Ye 15-06-16]]

[[Tianyi Luo 15-06-16]]

[[Dongxu Zhang 15-06-16]]

[[Askar 15-06-16]]

[[Xi Ma 15-06-16]]

Xi Ma 15-06-08

2015-06-14T03:20:43Z

Mx：以“Last Week: 1.Write the papper of similar-pair method for the journal. This Week: 1.Modify the paper of Interspeech2015.”为内容创建页面

Last Week:

1.Write the papper of similar-pair method for the journal.

This Week:

1.Modify the paper of Interspeech2015.

2015-06-08

2015-06-14T03:13:23Z

Mx：

[[Rong Liu 15-06-08]]

[[Tianyi Luo 15-06-08]]

[[Zipeng Ye 15-06-08]]

[[Askar 15-06-08]]

[[Mengyuan Zhao 15-06-08]]

[[Zhiyuan Tang 15-06-08]]

[[Xi Ma 15-06-08]]

Xi Ma 15-06-02

2015-06-03T01:19:38Z

Mx：以“Last Week: 1.Write the paper about similar-pair method. This Week: 1.Modify the paper about similar-pair method.”为内容创建页面

Last Week:

1.Write the paper about similar-pair method.

This Week:

1.Modify the paper about similar-pair method.

2015-06-01

2015-06-03T00:56:23Z

Mx：

[[Tianyi Luo 15-06-01]]

[[Askar 15-06-01]]

[[Zipeng Ye 15-06-01]]

[[Dongxu Zhang 15-06-01]]

[[Rong Liu 15-06-01]]

[[Yiqiao Pan 15-06-01]]

[[Chao Xing 15-06-02]]

[[Xi Ma 15-06-02]]

Xi Ma 15-05-25

2015-05-30T05:34:24Z

Mx：以“Last Week: 1.Solve the problem of tag language model for Sinovoice. 2.Test the performance of similar-pair method by using Chinese acoustic model. This Week: 1.W...”为内容创建页面

Last Week:

1.Solve the problem of tag language model for Sinovoice.

2.Test the performance of similar-pair method by using Chinese acoustic model.

This Week:

1.Writing paper on similar-pair method.

2015-05-24

2015-05-30T04:55:43Z

Mx：

[[Dongxu Zhang 15-05-24 ]]

[[Miao Fan 15-05-24 ]]

[[Tianyi Luo 15-05-24]]

[[Zipeng Ye 15-05-24]]

[[Xiaoxi Wang 15-05-24]]

[[Mengyuan Zhao 15-05-24]]

[[Zhiyuan Tang 15-05-24]]

[[Zhiyong Zhang 15-05-24]]

[[Xuewei Zhang 15-05-24]]

[[Lantian Li 15-05-25]]

[[Xi Ma 15-05-25]]

Xi Ma 15-05-18

2015-05-22T01:51:40Z

Mx：以“Last Week 1.Solve the problem of xiaomi by using tag model. This Week 1.Test the performance of the similar-pair method in bilingual recognition.”为内容创建页面

Last Week

1.Solve the problem of xiaomi by using tag model.

This Week

1.Test the performance of the similar-pair method in bilingual recognition.

2015-05-17

2015-05-22T01:24:00Z

Mx：

[[Miao Fan 15-05-17]]

[[Zhiyuan Tang 15-05-17]]

[[Chao Xing 15-05-17]]

[[Xiaoxi Wang 15-05-17]]

[[Mengyuan Zhao 15-05-17]]

[[Tianyi Luo 15-05-17]]

[[Rong Liu 15-05-17]]

[[Zhongwei Yao 15-05-17]]

[[Zhiyong Zhang 15-05-17]]

[[Xiangyu Zeng 15-05-17]]

[[Xuewei Zhang 15-05-17]]

[[Zipeng Ye 15-05-17]]

[[Lantian Li 15-05-18]]

[[Chao Liu 15-05-18]]

[[Xi Ma 15-05-18]]

Xi Ma 15-05-05

2015-05-07T01:22:22Z

Mx：以“Last Week: 1.Solve the problem of the need of xiaomi for Sinovoice. 2.Test the performance of similar-pair method in Chinese words. This Week: 1.Test the perfor...”为内容创建页面

Last Week:

1.Solve the problem of the need of xiaomi for Sinovoice.

2.Test the performance of similar-pair method in Chinese words.

This Week:

1.Test the performance of similar-pair method in English word.

2015-05-04

2015-05-07T00:55:40Z

Mx：

[[Lantian Li 15-05-05]]

[[Mengyuan Zhao 15-05-05]]

[[Zhiyong Zhang 15-05-05]]

[[Zipeng Ye 15-05-05]]

[[Xuewei Zhang 15-05-05]]

[[Xi Ma 15-05-05]]

Xi Ma 2015-04-27

2015-04-29T02:54:09Z

Mx：以“Last Week: 1.Test the performance of similar-pair method, which using similarity of word vector. This Week: 1.Try using the tag language model to solve the need o...”为内容创建页面

Last Week:

1.Test the performance of similar-pair method, which using similarity of word vector.

This Week:

1.Try using the tag language model to solve the need of xiaomi.

2015-04-27

2015-04-29T02:46:45Z

Mx：

[[Mengyuan Zhao 2015-04-27]]

[[Zipeng Ye 2015-04-27]]

[[Zhiyuan Tang 2015-04-27]]

[[Zhiyong Zhang 2015-04-27]]

[[Rong Liu 2015-04-27]]

[[Xi Ma 2015-04-27]]

Xi Ma 15-04-20

2015-04-21T01:47:44Z

Mx：以“Last Week: 1.Solve the problem of biglm when using language model prune. 2.Test the performance of two similar-pair method. This Week: 1.Test the performance of...”为内容创建页面

Last Week:

1.Solve the problem of biglm when using language model prune.

2.Test the performance of two similar-pair method.

This Week:

1.Test the performance of the similar-pair method of using similarity.

2.Help the engineer of SinoVoice to achieve the needs of XiaoMi.

2015-04-20

2015-04-21T01:17:49Z

Mx：

[[Mengyuan Zhao 15-04-20]]

[[Zipeng Ye 15-04-20]]

[[Dongxu Zhang 15-04-20]]

[[Zhiyuan Tang 15-04-20]]

[[Lantian Li 15-04-20]]

[[Rong Liu 15-04-20]]

[[Xi Ma 15-04-20]]

Xi Ma 2015-04-13

2015-04-14T06:24:49Z

Mx：以“Last Week 1.Solve the problem of biglm-decoding in tag language model. This Week 1.Extract some new test sets to observe the difference of three kinds of methods:...”为内容创建页面

Last Week

1.Solve the problem of biglm-decoding in tag language model.

This Week

1.Extract some new test sets to observe the difference of three kinds of methods: simple similar-pair method, the similar-pair method which using word frequency, the similar-pair method which using word similarity.

2015-04-13

2015-04-14T06:07:34Z

Mx：

[[Mengyuan Zhao 2015-04-13]]

[[Rong Liu 2015-04-13]]

[[Chao Xing 2015-04-13]]

[[Tianyi Luo 2015-04-13]]

[[Xiaoxi Wang 2015-04-13]]

[[Dongxu Zhang 2015-04-13]]

[[Zipeng Ye 2015-04-13]]

[[Xuewei Zhang 2015-04-13]]

[[Zhiyuan Tang 2015-04-13]]

[[Chao Liu 2015-04-13]]

[[Xi Ma 2015-04-13]]

文件:2015-4-1-Xi Ma-Bi-month report.pdf

2015-04-09T09:39:00Z

Mx：

Bi-monthly-2015-03

2015-04-09T09:37:11Z

Mx：

==小组总评==

*学术 8.64
*工作 8.71
*创新 7.86
*公平 9.07
*工资 8.29
==存在问题==
*GPU不足
*学术力量分散
*整个组多沟通学术
*服务器噪音太大
*方向多倾向于NLP

==个人评价==
[[bi-monthly-2015-03-result|result]]

==报告==

*[[媒体文件:Bi-monthly_report-2015-03.pdf|王东]]

*[[媒体文件:2015.01-03张雪薇季度总结.pdf|张雪薇]]

*[[媒体文件:TZY_20150331.pdf|汤志远]]

*[[媒体文件:个人双月总结-殷实150401.pdf|殷实]]

*[[媒体文件:Yiye_Lin双月3月.pdf|林一叶]]

*[[媒体文件:刘荣1-3月度总结.pdf|刘荣]]

*[[媒体文件:zhangzy_20150103.pdf|张之勇]]

*[[媒体文件:Liuc_201503.pdf|刘超]]

*[[媒体文件:Zengxy_201503.pdf|曾翔宇]]

*[[媒体文件:2015-04-01 Tianyi Luo's bi-monthly report.pdf|骆天一]]

*[[媒体文件:2015-4-1-Xi Ma-Bi-month report.pdf|马习]]

Bi-monthly-2015-03

2015-04-09T09:33:33Z

Mx：

文件:2015-4-1-Xi Ma-Bi-month report.ppt

2015-04-09T09:32:03Z

Mx：

Bi-monthly-2015-03

2015-04-09T09:28:44Z

Mx：/* 报告 */

Xi Ma 2015-04-07

2015-04-09T09:26:43Z

Mx：以“Last Week: 1.Using new corpus to train a bigger language model. 2.Extract the new test set from other bigger test set to vertify multiple similar-pair method. Th...”为内容创建页面

Last Week:

1.Using new corpus to train a bigger language model.

2.Extract the new test set from other bigger test set to vertify multiple similar-pair method.

This Week:

1.Solve the problem of tag-lm method.

2015-04-07

2015-04-09T09:18:40Z

Mx：

[[Chao Xing 2015-04-07]]

[[Zhiyong Zhang 2015-04-07]]

[[Xiaoxi Wang 2015-04-07]]

[[Yiqiao Pan 2015-04-07]]

[[Xuewei Zhang 2015-04-7]]

[[Mengyuan Zhao 2015-04-07]]

[[Chao Liu 2015-04-07]]

[[Tianyi Luo 2015-04-07]]

[[Rong Liu 2015-04-07]]

[[Dongxu Zhang 2015-04-07]]

[[Zhiyuan Tang 2015-04-07]]

[[Askar 2015-04-07]]

[[Miao Fan 2015-04-07]]

[[Xiangyu Zeng 2015-04-07]]

[[Lantian Li 2015-04-08]]

[[Fanhu Bie 2015-04-07]]

[[Xi Ma 2015-04-07]]

Public tools

2015-04-03T06:59:30Z

Mx：/* Micro-FST Composition Tool */

===JCLTS===

JCLTS is a toolkit which uses joint-multigram model plus CRF to generate predictions of a stream given another stream. The JMM is responsible for a simple model to obtain raw alignment of the two streams, and the CRF is used to train a powerful model based on the alignment.
ref to:Dong Wang, Simon King, "Letter-to-Sound Pronunciation Prediction using Conditional Random Field", IEEE Signal Processing Letters, vol 18, no.2, February 2011 , pp 122-125.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/lts.v1.0.tar.gz download]

===GFCC===
Time domain gamma tone cepstral coefficient (GFCC) provided by Jun Qi, EE dep. Tsinghua Univ., China.
ref to:"Auditory feature based on Gammatone filters for robust speech recognition", ISCAS 2013.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/gfcc.v0.2.tgz download]

===FSTi===

This FSTi tookit contains a set of indexing tools developed in CSLT, Tsinghua University. The main purpose of FSTi is to provide a quick and easy way to construct an entire STD system when combining with some standard tools, including:
HTK from Cambridge: http://htk.eng.cam.ac.uk/
lattice-tool from SRI: http://www-speech.sri.com/projects/srilm/manpages/lattice-tool.1.html
OpenFST: http://www.openfst.org/twiki/bin/view/FST/WebHome

FSTi provides three integration approaches, any can be used to construct a full practical STD system:

1. HTK + lat2fst: standard FST-based indexing[2,3] (liblse from BUT required).

2. HTK + lattice-tool + ridx: standard ngram indexing[4].

3. HTK + lattice-tool + ngram2fst: ngram-based FST indexing[1].

For more details, please refer to the following paper on Interspeech[1].
[1] Chao Liu, Dong Wang, "N-gram FST indexing for spoken term detection", Interspeech 2012.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/FSTi.tar.gz download]

===HCNSC===

We publish the heterogeneous CNSC code plus an example task on speech separation. For details please refer to
Heterogeneous convolutive non-negative sparse coding. Dong Wang, Javier Tejedor, submiited to Interspeech.
This fold contains the following directory:
1. olcnsc. The core of online convolutive non-negative sparse coding, extended with heterogeneous learning
2. utest. An example task for speech separation. This includes a basic invokation example and two scripts that demonstrate how to search for optimal base distributions.
3. util. Some util scripts that assit utest.
You can use and distribute this code freely for research purpose. The authors do not take any responsibility for any damage caused by running the code.
Any comments, questions, bugs.. are particularly welcome.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/hcnsc.tar.gz download]

===Online CNSC===

This package contains my matlab code for online learning approach for convolutive non-negative sparse coding (OLCNSC). Refer to the following paper on interspeech 2011:
Dong Wang, Nicholas Evans, "Online Pattern Learning for Convolutive Non-negative Sparse Coding"

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/olcnsc.tar.gz download]

===Crawler based on keywords ===

This is a crawler which can get the Top-K relevant webpages' contents returned by Search Engine e.g. Bing with keywords e.g. yahoo, 百度(Chinese writing of Baidu).
This code is implemented by Java. The tool supports Chinese keywords and English keywords.
I share the source code in the following website. Please download the jar files, readme document and source code files.

[http://pan.baidu.com/s/1bnrmWhx download]

===Sina weibo crawler===

This is a crawler to get sina weibo's information including body, comments, number of forwards and etc. This code is implemented by Python. This crawler will get weibo 340M/day if you conduct uninterrupted running for 24 hours.
I share the source code in the following website. Please download the readme document and source code files.

[http://pan.baidu.com/s/1qW9LqH2 download]

===Micro-FST Composition Tool===

This package contains my python and shell script for joining the micro-FST into the special position of another FST. In addition, this toolkit has solved the determinization problem.

[http://cslt.riit.tsinghua.edu.cn:8081/pubtools/fstemb/tag-based_lm.tar.gz download]

Public tools

2015-04-03T06:58:45Z

Mx：

===JCLTS===

JCLTS is a toolkit which uses joint-multigram model plus CRF to generate predictions of a stream given another stream. The JMM is responsible for a simple model to obtain raw alignment of the two streams, and the CRF is used to train a powerful model based on the alignment.
ref to:Dong Wang, Simon King, "Letter-to-Sound Pronunciation Prediction using Conditional Random Field", IEEE Signal Processing Letters, vol 18, no.2, February 2011 , pp 122-125.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/lts.v1.0.tar.gz download]

===GFCC===
Time domain gamma tone cepstral coefficient (GFCC) provided by Jun Qi, EE dep. Tsinghua Univ., China.
ref to:"Auditory feature based on Gammatone filters for robust speech recognition", ISCAS 2013.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/gfcc.v0.2.tgz download]

===FSTi===

This FSTi tookit contains a set of indexing tools developed in CSLT, Tsinghua University. The main purpose of FSTi is to provide a quick and easy way to construct an entire STD system when combining with some standard tools, including:
HTK from Cambridge: http://htk.eng.cam.ac.uk/
lattice-tool from SRI: http://www-speech.sri.com/projects/srilm/manpages/lattice-tool.1.html
OpenFST: http://www.openfst.org/twiki/bin/view/FST/WebHome

FSTi provides three integration approaches, any can be used to construct a full practical STD system:

1. HTK + lat2fst: standard FST-based indexing[2,3] (liblse from BUT required).

2. HTK + lattice-tool + ridx: standard ngram indexing[4].

3. HTK + lattice-tool + ngram2fst: ngram-based FST indexing[1].

For more details, please refer to the following paper on Interspeech[1].
[1] Chao Liu, Dong Wang, "N-gram FST indexing for spoken term detection", Interspeech 2012.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/FSTi.tar.gz download]

===HCNSC===

We publish the heterogeneous CNSC code plus an example task on speech separation. For details please refer to
Heterogeneous convolutive non-negative sparse coding. Dong Wang, Javier Tejedor, submiited to Interspeech.
This fold contains the following directory:
1. olcnsc. The core of online convolutive non-negative sparse coding, extended with heterogeneous learning
2. utest. An example task for speech separation. This includes a basic invokation example and two scripts that demonstrate how to search for optimal base distributions.
3. util. Some util scripts that assit utest.
You can use and distribute this code freely for research purpose. The authors do not take any responsibility for any damage caused by running the code.
Any comments, questions, bugs.. are particularly welcome.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/hcnsc.tar.gz download]

===Online CNSC===

This package contains my matlab code for online learning approach for convolutive non-negative sparse coding (OLCNSC). Refer to the following paper on interspeech 2011:
Dong Wang, Nicholas Evans, "Online Pattern Learning for Convolutive Non-negative Sparse Coding"

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/olcnsc.tar.gz download]

===Crawler based on keywords ===

This is a crawler which can get the Top-K relevant webpages' contents returned by Search Engine e.g. Bing with keywords e.g. yahoo, 百度(Chinese writing of Baidu).
This code is implemented by Java. The tool supports Chinese keywords and English keywords.
I share the source code in the following website. Please download the jar files, readme document and source code files.

[http://pan.baidu.com/s/1bnrmWhx download]

===Sina weibo crawler===

This is a crawler to get sina weibo's information including body, comments, number of forwards and etc. This code is implemented by Python. This crawler will get weibo 340M/day if you conduct uninterrupted running for 24 hours.
I share the source code in the following website. Please download the readme document and source code files.

[http://pan.baidu.com/s/1qW9LqH2 download]

===Micro-FST Composition Tool===

This package contains my python and sheel script for joining the micro-FST into the special position of another FST. In addition, this toolkit has solved the determinization problem.

[http://cslt.riit.tsinghua.edu.cn:8081/pubtools/fstemb/tag-based_lm.tar.gz download]

Public tools

2015-04-03T06:37:08Z

Mx：

===JCLTS===

JCLTS is a toolkit which uses joint-multigram model plus CRF to generate predictions of a stream given another stream. The JMM is responsible for a simple model to obtain raw alignment of the two streams, and the CRF is used to train a powerful model based on the alignment.
ref to:Dong Wang, Simon King, "Letter-to-Sound Pronunciation Prediction using Conditional Random Field", IEEE Signal Processing Letters, vol 18, no.2, February 2011 , pp 122-125.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/lts.v1.0.tar.gz download]

===GFCC===
Time domain gamma tone cepstral coefficient (GFCC) provided by Jun Qi, EE dep. Tsinghua Univ., China.
ref to:"Auditory feature based on Gammatone filters for robust speech recognition", ISCAS 2013.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/gfcc.v0.2.tgz download]

===FSTi===

This FSTi tookit contains a set of indexing tools developed in CSLT, Tsinghua University. The main purpose of FSTi is to provide a quick and easy way to construct an entire STD system when combining with some standard tools, including:
HTK from Cambridge: http://htk.eng.cam.ac.uk/
lattice-tool from SRI: http://www-speech.sri.com/projects/srilm/manpages/lattice-tool.1.html
OpenFST: http://www.openfst.org/twiki/bin/view/FST/WebHome

FSTi provides three integration approaches, any can be used to construct a full practical STD system:

1. HTK + lat2fst: standard FST-based indexing[2,3] (liblse from BUT required).

2. HTK + lattice-tool + ridx: standard ngram indexing[4].

3. HTK + lattice-tool + ngram2fst: ngram-based FST indexing[1].

For more details, please refer to the following paper on Interspeech[1].
[1] Chao Liu, Dong Wang, "N-gram FST indexing for spoken term detection", Interspeech 2012.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/FSTi.tar.gz download]

===HCNSC===

We publish the heterogeneous CNSC code plus an example task on speech separation. For details please refer to
Heterogeneous convolutive non-negative sparse coding. Dong Wang, Javier Tejedor, submiited to Interspeech.
This fold contains the following directory:
1. olcnsc. The core of online convolutive non-negative sparse coding, extended with heterogeneous learning
2. utest. An example task for speech separation. This includes a basic invokation example and two scripts that demonstrate how to search for optimal base distributions.
3. util. Some util scripts that assit utest.
You can use and distribute this code freely for research purpose. The authors do not take any responsibility for any damage caused by running the code.
Any comments, questions, bugs.. are particularly welcome.

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/hcnsc.tar.gz download]

===Online CNSC===

This package contains my matlab code for online learning approach for convolutive non-negative sparse coding (OLCNSC). Refer to the following paper on interspeech 2011:
Dong Wang, Nicholas Evans, "Online Pattern Learning for Convolutive Non-negative Sparse Coding"

[http://cslt.riit.tsinghua.edu.cn:8081/homepages/wangd/public/tools/zip/olcnsc.tar.gz download]

===Crawler based on keywords ===

This is a crawler which can get the Top-K relevant webpages' contents returned by Search Engine e.g. Bing with keywords e.g. yahoo, 百度(Chinese writing of Baidu).
This code is implemented by Java. The tool supports Chinese keywords and English keywords.
I share the source code in the following website. Please download the jar files, readme document and source code files.

[http://pan.baidu.com/s/1bnrmWhx download]

===Sina weibo crawler===

This is a crawler to get sina weibo's information including body, comments, number of forwards and etc. This code is implemented by Python. This crawler will get weibo 340M/day if your conduct uninterrupted running for 24 hours.
I share the source code in the following website. Please download the readme document and source code files.

[http://pan.baidu.com/s/1qW9LqH2 download]

===Micro-FST Composition Tool===

This package contains my python and sheel script for joining the micro-FST into the special position of another FST. In addition, this toolkit has solved the determinization problem.

[http://cslt.riit.tsinghua.edu.cn:8081/pubtools/fstemb/tag-based_lm.tar.gz]

Bi-monthly-2015-01

2015-04-01T01:26:57Z

Mx：

Bi-monthly-2015-01

2015-04-01T01:08:50Z

Mx：

Bi-monthly-2015-01

2015-04-01T01:08:34Z

Mx：

Xi Ma 2015-03-30

2015-03-30T12:24:37Z

Mx：以“Last Week: 1.Finish the paper about multiple similar-pair method for the Conference: Interspeech 2015. This Week: 1.Try the method of using similarity to adjust t...”为内容创建页面

Last Week:

1.Finish the paper about multiple similar-pair method for the Conference: Interspeech 2015.

This Week:

1.Try the method of using similarity to adjust the weight of new arcs.

2.Modify the code to decrease the influence of silence phone.

2015-03-30

2015-03-30T12:01:41Z

Mx：

[[Chao Xing 2015-03-30]]

[[Mengyuan Zhao 2015-03-30]]

[[Xiangyu Zeng 2015-03-30]]

[[Rong Liu 2015-03-30]]

[[Shi Yin 2015-03-30]]

[[Fanhu Bie 2015-03-30]]

[[Xiaoxi Wang 2015-03-30]]

[[Tianyi Luo 2015-03-30]]

[[Zhiyong Zhang 2015-03-30]]

[[Xi Ma 2015-03-30]]

Asr-intern-week

2015-03-30T00:28:21Z

Mx：/* Intern Working Timetable */

==Intern Working Timetable==

{|class=wikitable
! !!周一 !! 周二 !! 周三 !! 周四 !! 周五 !! 周六 !! 周日
|-
|Xiang Yu Zeng|| ok ||下午 ||下午 || 下午 ||x ||x || ok
|-
|Bin Yuan ||OK ||OK ||OK ||上午 ||OK ||X || X
|-
|Dong Xu Zhang||OK ||下午 ||OK ||下午 ||OK ||X ||X
|-
|Yiye Lin ||OK || OK ||OK || OK || OK || X || X
|-
|Chao Xing ||All ||All ||All ||All ||All ||OX ||OX
|-
|Li cao || 上午+晚上 || OK （公司） || 下午+晚上 || 下午 || 上午+晚上 || OK(公司) || X
|-
|Mian Wang || 下午 || OK || OK || X || OK || X || X
|-
|Xi Ma || OK || OK || OK || OK || OK || X || X
|-
|}

Xi Ma 2015-03-23

2015-03-25T02:19:52Z

Mx：以“Last Week: 1.Modify the related code to enhance the English words by using multiple similar Chinese words. 2.Prepare experiment data for the paper about using mult...”为内容创建页面

Last Week:

1.Modify the related code to enhance the English words by using multiple similar Chinese words.

2.Prepare experiment data for the paper about using multiple similar Chinese words to enhance English words.

This Week

1.Finish paper about using multiple similar Chinese words to enhance English words.

2015-03-23

2015-03-24T08:24:44Z

Mx：

[[Rong Liu 2015-03-23]]

[[Xiaoxi Wang 2015-03-23]]

[[Mengyuan Zhao 2015-03-23]]

[[Shi Yin 2015-03-23]]

[[Zipeng Ye 2015-03-23]]

[[Dongxu Zhang 2015-03-23]]

[[Chao Liu 2015-03-23]]

[[Xuewei Zhang 2015-03-23]]

[[Zhiyuan Tang 2015-03-23]]

[[Lantian Li 2015-03-23]]

[[Zhiyong Zhang 2015-03-23]]

[[Xiangyu Zeng 2015-03-23]]

[[Xi Ma 2015-03-23]]

Xi Ma 2015-03-16

2015-03-17T01:07:37Z

Mx：以“Last Week: 1.Finish the secend entrance exams for postgraduates. This Week: 1.Try using the weight of multi-high-frequency words to adjust the weight of low-frequ...”为内容创建页面

Last Week:

1.Finish the secend entrance exams for postgraduates.

This Week:

1.Try using the weight of multi-high-frequency words to adjust the weight of low-frequency words.

2.Using the experiment data of micrograph to compare the experiment of district tag-graph.

2015-03-15

2015-03-17T00:56:58Z

Mx：

[[Rong Liu 2015-03-15]]

[[Tianyi Luo 2015-03-15]]

[[Lantian Li 2015-03-16]]

[[Mengyuan Zhao 2015-03-16]]

[[Zipeng Ye 2015-03-16]]

[[Zhiyuan Tang 2015-03-16]]

[[Chao Liu 2015-03-16]]

[[Xuewei Zhang 2015-03-16]]

[[Xi Ma 2015-03-16]]