Public Research Tools

Speech recognition

1. Noise robustness

http://www1.icsi.berkeley.edu/Speech/papers/gelbart-ms/pointers/

2. Qualcomm-ICSI-OGI front end

http://www1.icsi.berkeley.edu/Speech/papers/qio/

3. LTSM/RNN training, GPU&deep supported

http://sourceforge.net/projects/currennt/

4. Sequence CRF

http://research.microsoft.com/en-us/projects/scarf/

5. RNNLM: RNN LM toolkit

http://www.fit.vutbr.cz/~imikolov/rnnlm/

6. RWTHLM: RNN LTSM toolkit

http://www-i6.informatik.rwth-aachen.de/web/Software/rwthlm.php

7. cslm: NN LM, GPU supported

http://www-lium.univ-lemans.fr/~cslm/

8. nplm: NN LM, large scale data

http://nlg.isi.edu/software/nplm/

9. OpenSmile: speech feature extraction tool

http://www.audeering.com/research/opensmile

10. praat: famous speech signal manipulation tool

http://www.fon.hum.uva.nl/praat/

11. openEAR: speech emotion detection

http://sourceforge.net/projects/openart/

12. REVERBE: tool from the reverbe challenge

http://reverb2014.dereverberation.com/

13. HTK: ASR toolkit from Cambridge

http://htk.eng.cam.ac.uk/

14. Julius: Japan ASR decoder

http://julius.sourceforge.jp/en_index.php

15. Juier: ASR decoder from AMIDA

https://www.idiap.ch/scientific-research/resources/Juicer

16. sphinx: cmu speech recognition

http://sphinxsearch.com/

17. OpenFST: toolkit to manipulate FSTs

http://www.openfst.org/twiki/bin/view/FST/WebHome

Machine Learning

1. general Bayesian inference: doc and tool

http://ksvanhorn.com/bayes/free-bayes-software.html

2. The Variantional Bayesian toolkit:

http://www.gatsby.ucl.ac.uk/vbayes/vbsoftware.html

The sampling based Bayesian approach can be obtained here:

http://www.mrc-bsu.cam.ac.uk/bugs/

3. Topic models from David Blei

http://www.cs.princeton.edu/~blei/topicmodeling.html

4. MCMC approaches also here

http://www.mppmu.mpg.de/bat/

http://www.mpe.mpg.de/~aws/BayesForum_201204_KK.pdf

5. Topic models Biography

http://www.cs.princeton.edu/~mimno/topics.html

6. Gibbs LDA

http://gibbslda.sourceforge.net/

7. Tools for DPMM

Jacobei

https://github.com/jacobeisenstein/DPMM

Scikit

http://scikit-learn.org/0.11/index.html

Hains

http://code.google.com/p/haines/

8. Sparse SVMs

http://www.enm.bris.ac.uk/staff/xkh/

9. Lasso

http://www-stat.stanford.edu/~tibs/lasso.html

10. Sparse LU

http://crd-legacy.lbl.gov/~xiaoye/SuperLU/

11. Ensemble SVM

http://homes.esat.kuleuven.be/~claesenm/ensemblesvm/

12. Online learning toolkit

http://www.cais.ntu.edu.sg/~chhoi/libol/

13. VBEM-GMM

http://www.cs.ubc.ca/~murphyk/Software/VBEMGMM/index.html

14. pylearn2

http://deeplearning.net/software/pylearn2/

15. Deep learning resources

http://meta-guide.com/software-meta-guide/100-best-github-deep-learning/

16. Computational Network Toolkit (CNTK)

https://cntk.codeplex.com/

17. SPMF: A Java Open-Source Pattern Mining Library

http://www.philippe-fournier-viger.com/spmf/index.php

18. libSVM and liblinear: toolkit from Taiwan for SVM and linear model learning

http://www.csie.ntu.edu.tw/~cjlin/libsvm/

http://www.csie.ntu.edu.tw/~cjlin/liblinear/

19. CRF++

http://crfpp.googlecode.com/svn/trunk/doc/index.html?source=navbar

20. Hyperopt: Hyper-parameter Optimization

http://github.com/hyperopt/hyperopt

21. CNTK: computational network toolkit from MS

https://cntk.codeplex.com/SourceControl/latest

22. svmlight

http://svmlight.joachims.org/

23. t-SNE: a toolkit for drawing high-dim vectors

http://homepage.tudelft.nl/19j49/t-SNE.html

24. GURLS: Grand Unified Regularized Least Squares

http://lcsl.mit.edu/gurls.html

25. Bayesopt

https://bitbucket.org/rmcantin/bayesopt

NLP toolkits and resources

1. Stanford tools

http://nlp.stanford.edu/software/

2. Traditional Chinese public dictionary and statistics

http://www.edu.tw/files/site_content/m0001/pin/yu7.htm?open

3. Idiom Traditional Chinese public words

http://dict.idioms.moe.edu.tw/cydic/index.htm

4. RNN toolkit from microsoft

http://research.microsoft.com/en-us/projects/rnn/

5. A bunch of resources

http://www-nlp.stanford.edu/links/statnlp.html

6. SEMPRE (QA toolkit)

http://www-nlp.stanford.edu/software/sempre/

7. WEKA: probably the most famous ML toolkit

http://www.cs.waikato.ac.nz/ml/weka/

8. word2vector: word vector embedding from google

http://code.google.com/p/word2vec/

9. moses: SMT tool

http://www.statmt.org/moses/

10. joshua: SMT tool

http://joshua-decoder.org/5.0/pipeline.html

11. mgizapp: SMT alignment tool

http://www.kyloo.net/software/doku.php/mgiza:overview

12. SRILM toolkit

http://www.speech.sri.com/projects/srilm/

13. IRSTLM

http://hlt.fbk.eu/en/irstlm

14. IKAnalyze: word segment tool

http://code.google.com/p/ik-analyzer/downloads/list

15. ICTCLA word segment tool

http://www.ictclas.org/

SID toolits

1. Alize from Avignon

http://mistral.univ-avignon.fr/download_en.html

2. Idiap: Xbob speaker recognition system

https://github.com/bioidiap/xbob.spkrec

http://www.idiap.ch/~marcel/professional/Resources.html

3. SPEAR: A Speaker Recognition Toolkit based on Bob

https://pypi.python.org/packages/source/b/bob.spear/bob.spear-1.1.2.zip

Computer Vision

1. OpenCV: the most famous CV tool

http://opencv.org/

Other tools

1. MathType: MS word plugin for math equations from Latex to word or vice versa.

http://rj.baidu.com/soft/detail/14927.html?ald