Difference between revisions of "Software"
From rosp
m (→Automatic speech recognition) |
m (→Automatic speech recognition) |
||
Line 10: | Line 10: | ||
!scope="col" width="40px" | licence | !scope="col" width="40px" | licence | ||
!scope="col" width="40px" | platforms | !scope="col" width="40px" | platforms | ||
+ | !scope="col" width="40px" | links | ||
+ | !scope="col" width="40px" | extensions | ||
!scope="col" width="40px" | language | !scope="col" width="40px" | language | ||
!scope="col" width="40px" | VAD | !scope="col" width="40px" | VAD | ||
Line 20: | Line 22: | ||
!scope="col" width="40px" | hardware optimization | !scope="col" width="40px" | hardware optimization | ||
!scope="col" width="40px" | online ASR | !scope="col" width="40px" | online ASR | ||
− | |||
− | |||
− | |||
− | |||
!scope="col" width="40px" | training recipes | !scope="col" width="40px" | training recipes | ||
!scope="col" width="40px" | reproducible results | !scope="col" width="40px" | reproducible results | ||
Line 31: | Line 29: | ||
|{{yes|Yes}} | |{{yes|Yes}} | ||
|{{some|limited [https://raw.githubusercontent.com/cmusphinx/sphinx4/master/license.terms Copyright, allows modif.]}} | |{{some|limited [https://raw.githubusercontent.com/cmusphinx/sphinx4/master/license.terms Copyright, allows modif.]}} | ||
− | |{{yes| | + | |{{yes|Windows, Linux, OSX (Sphinx4) / Raspberry-pi, iPhone, Android (pocketsphinx)}} |
− | |Sphinx4 | + | |[http://cmusphinx.sourceforge.net/ website] |
+ | [http://www.cs.cmu.edu/~rsingh/homepage/papers/icassp03-sphinx4_2.pdf paper] | ||
+ | [https://www.cs.cmu.edu/~awb/papers/ICASSP2006/0100185.pdf paper] | ||
+ | [http://sourceforge.net/p/cmusphinx/mailman/ mail-list] | ||
+ | [http://sourceforge.net/p/cmusphinx/discussion/ forum] | ||
+ | [https://github.com/cmusphinx github] | ||
+ | | | ||
+ | |Java (Sphinx4), C (pocketsphinx) | ||
+ | |{{no|No}} | ||
|{{yes|Yes}} | |{{yes|Yes}} | ||
|MFCC, PLP | |MFCC, PLP | ||
Line 40: | Line 46: | ||
|aligment, N-best, lattice rescoring | |aligment, N-best, lattice rescoring | ||
|Baum-Welch | |Baum-Welch | ||
− | |||
|{{yes|Yes}} | |{{yes|Yes}} | ||
− | |||
− | |||
− | |||
− | |||
− | |||
|[http://www.keithv.com/software/sphinx/ AURORA4 (WSJ0)] | |[http://www.keithv.com/software/sphinx/ AURORA4 (WSJ0)] | ||
| | | | ||
Line 55: | Line 55: | ||
|{{no|limited [http://htk.eng.cam.ac.uk/docs/license.shtml]}} | |{{no|limited [http://htk.eng.cam.ac.uk/docs/license.shtml]}} | ||
|{{yes|Windows, Linux, OSX}} | |{{yes|Windows, Linux, OSX}} | ||
+ | |[http://htk.eng.cam.ac.uk/download.shtml website] | ||
+ | [http://htk.eng.cam.ac.uk/docs/docs.shtml book] | ||
+ | [http://htk.eng.cam.ac.uk/mailing/subscribe_mail.shtml mail-list] | ||
+ | |[http://htk.eng.cam.ac.uk/extensions/index.shtml official], [http://htk.eng.cam.ac.uk/develop/atk.shtml ATK], [https://github.com/ramon-astudillo/custom_fe uncertainty decoding] | ||
|C | |C | ||
+ | |{{no|No}} | ||
|{{yes|Yes}} | |{{yes|Yes}} | ||
|MFCC, PLP | |MFCC, PLP | ||
Line 63: | Line 68: | ||
|aligment, N-best, lattice rescoring | |aligment, N-best, lattice rescoring | ||
|Baum-Welch | |Baum-Welch | ||
− | |||
|{{yes|Yes}} | |{{yes|Yes}} | ||
− | |||
− | |||
− | |||
− | |||
|[http://catalog.elra.info/product_info.php?cPath=37_40&products_id=693 AURORA2 (purch.)] [http://catalog.elra.info/index.php?cPath=37_40 AURORA3 (purch.)], [http://www.keithv.com/software/htk/ AURORA4 (WSJ0)], [http://spandh.dcs.shef.ac.uk/projects/chime/PCC/data/pcchome.tar.gz CHIME-1], [ftp://ftp.dcs.shef.ac.uk/share/spandh/chime_challenge/grid/eval_tools_grid.tgz CHIME-2-I], [http://reverb2014.dereverberation.com/tools/REVERB_TOOLS_FOR_ASR_ver2.0.tgz REVERB] | |[http://catalog.elra.info/product_info.php?cPath=37_40&products_id=693 AURORA2 (purch.)] [http://catalog.elra.info/index.php?cPath=37_40 AURORA3 (purch.)], [http://www.keithv.com/software/htk/ AURORA4 (WSJ0)], [http://spandh.dcs.shef.ac.uk/projects/chime/PCC/data/pcchome.tar.gz CHIME-1], [ftp://ftp.dcs.shef.ac.uk/share/spandh/chime_challenge/grid/eval_tools_grid.tgz CHIME-2-I], [http://reverb2014.dereverberation.com/tools/REVERB_TOOLS_FOR_ASR_ver2.0.tgz REVERB] | ||
|ETSI-AFE-AURORA2 [http://aurora.hsnr.de/download/Aurora2_afe_v1_1.pdf paper] (see AURORA2 purch.) | |ETSI-AFE-AURORA2 [http://aurora.hsnr.de/download/Aurora2_afe_v1_1.pdf paper] (see AURORA2 purch.) | ||
Line 77: | Line 77: | ||
|{{Yes|Apache 2.0}} | |{{Yes|Apache 2.0}} | ||
|{{some|Windows (not mantained as of 2014), Linux, OSX}} | |{{some|Windows (not mantained as of 2014), Linux, OSX}} | ||
+ | |[http://kaldi.sourceforge.net/about.html website] | ||
+ | [http://homepages.inf.ed.ac.uk/aghoshal/pubs/asru11-kaldi.pdf paper] | ||
+ | [http://sourceforge.net/p/kaldi/mailman/kaldi-users/ mail-list] | ||
+ | [http://sourceforge.net/p/kaldi/discussion/ forum] | ||
+ | [http://kaldi.sourceforge.net/install.html SVN] | ||
+ | | | ||
|C++ | |C++ | ||
+ | |{{yes|BLAS, LAPACK, GPU (for DNNs)}} | ||
|{{yes|Yes}} | |{{yes|Yes}} | ||
|MFCC, PLP | |MFCC, PLP | ||
Line 85: | Line 92: | ||
|Uses OpenFST, aligment, N-best, lattice rescoring | |Uses OpenFST, aligment, N-best, lattice rescoring | ||
|Baum-Welch, MMI (boosted), MC, feature-based, sequence training | |Baum-Welch, MMI (boosted), MC, feature-based, sequence training | ||
− | |||
|{{yes|Yes}} | |{{yes|Yes}} | ||
− | |||
− | |||
− | |||
− | |||
|[http://kaldi.sourceforge.net/data_prep.html AURORA4 (WSJ0)], CHIME-2 | |[http://kaldi.sourceforge.net/data_prep.html AURORA4 (WSJ0)], CHIME-2 | ||
|Weniger2014-REVERB [http://reverb2014.dereverberation.com/workshop/reverb2014-papers/1569884459.pdf Paper] [http://www.mmk.ei.tum.de/~wen/REVERB_2014/kaldi_baseline.tar.gz Code] | |Weniger2014-REVERB [http://reverb2014.dereverberation.com/workshop/reverb2014-papers/1569884459.pdf Paper] [http://www.mmk.ei.tum.de/~wen/REVERB_2014/kaldi_baseline.tar.gz Code] | ||
Line 99: | Line 101: | ||
|{{some|[http://www.spraak.org/obtaining-spraak/license Academic/commercial]}} | |{{some|[http://www.spraak.org/obtaining-spraak/license Academic/commercial]}} | ||
|{{some|Windows ([http://www.spraak.org/obtaining-spraak/system-requirements limited]), Linux}} | |{{some|Windows ([http://www.spraak.org/obtaining-spraak/system-requirements limited]), Linux}} | ||
+ | |[http://www.spraak.org/ website] | ||
+ | [http://www.esat.kuleuven.be/psi/spraak/cgi-bin/get_file.cgi?/wambacq/interspeech08/is2008_spraak_v3.pdf paper] | ||
+ | [http://www.spraak.org/mailing-lists mail-list] | ||
+ | [http://sourceforge.net/p/kaldi/discussion/ forum] | ||
+ | [http://www.spraak.org/documentation/doxygen/doc/html/spr__svn.html SVN] | ||
+ | | | ||
|C, Python | |C, Python | ||
+ | |{{no|No}} | ||
|{{yes|Yes}} | |{{yes|Yes}} | ||
|MFCC, PLP | |MFCC, PLP | ||
Line 107: | Line 116: | ||
|aligment, N-best, lattice rescoring, paralel latices | |aligment, N-best, lattice rescoring, paralel latices | ||
|Baum-Welch | |Baum-Welch | ||
− | |{{ | + | |{{dunno}} |
− | |||
− | |||
− | |||
− | |||
− | |||
|[http://www.spraak.org/documentation/doxygen/doc/html/spr__mdt__example.html AURORA4] | |[http://www.spraak.org/documentation/doxygen/doc/html/spr__mdt__example.html AURORA4] | ||
| | | |
Revision as of 10:59, 3 September 2014
This page provides software grouped by application.
Contents
Automatic speech recognition
ASR engines | release / update | actively developed | licence | platforms | links | extensions | language | VAD | acoustic features | feature normalization / compensation | acoustic models | model adaptation / compensation | decoding techniques | training techniques | hardware optimization | online ASR | training recipes | reproducible results |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CMU Sphinx | 1986-* (Sphinx 4.1.0, pocketsphinx 0.8) | Yes | limited Copyright, allows modif. | Windows, Linux, OSX (Sphinx4) / Raspberry-pi, iPhone, Android (pocketsphinx) | website | Java (Sphinx4), C (pocketsphinx) | No | Yes | MFCC, PLP | CMN, Mel-Spectrum subtraction | GMM, Streams | MLLR, MAP | aligment, N-best, lattice rescoring | Baum-Welch | Yes | AURORA4 (WSJ0) | ||
HTK | 1993-2009 (3.4.1) | No | limited [1] | Windows, Linux, OSX | website | official, ATK, uncertainty decoding | C | No | Yes | MFCC, PLP | VTLN, CMS | GMM (Full Cov.), Tied-Mix, Streams | HLDA, MLLR (w/ reg. trees), CMLR (w/ adaptive training), MAP | aligment, N-best, lattice rescoring | Baum-Welch | Yes | AURORA2 (purch.) AURORA3 (purch.), AURORA4 (WSJ0), CHIME-1, CHIME-2-I, REVERB | ETSI-AFE-AURORA2 paper (see AURORA2 purch.) |
Kaldi | 2009-* (continous updates) | Yes | Apache 2.0 | Windows (not mantained as of 2014), Linux, OSX | website | C++ | BLAS, LAPACK, GPU (for DNNs) | Yes | MFCC, PLP | VTLN, CMVN | GMM (Full Cov.), SGMM, DNN | HLDA, STC, MLLT, MLLR, CMLLR (w/ reg. trees), Exponential transform | Uses OpenFST, aligment, N-best, lattice rescoring | Baum-Welch, MMI (boosted), MC, feature-based, sequence training | Yes | AURORA4 (WSJ0), CHIME-2 | Weniger2014-REVERB Paper Code | |
Spraak | 2012 (1.1) | No | Academic/commercial | Windows (limited), Linux | website | C, Python | No | Yes | MFCC, PLP | VTLN,CMN, MIDA, MDT Techniques | GMM, Tied-Mix, Exemplar based | CMLLR | aligment, N-best, lattice rescoring, paralel latices | Baum-Welch | ? | AURORA4 |
Speaker identification and verification
Speech enhancement and separation
Other applications
Contribute software
To contribute new software, please
- create an account and login
- go to the wiki page above corresponding to your application; if it does not exist yet, you may create it
- click on the "Edit" link at the top of the page and add a new section for your software (software is ordered by year of the latest version)
- click on the "Save page" link at the bottom of the page to save your modifications
Please make sure to provide the following information:
- name of the software and year of the latest version
- authors, institution, contact information
- link to the software, ideally including a short demo, and to the external libraries needed
- short description (functionalities, inputs and outputs, programming language, operating system, license, etc) and link to a paper/report describing the software, if any
- whether running on well-known baselines (Aurora-2, Aurora-4, Switchboard, CHiME, etc) is included or requires wrapping by the user
In order to save storage space, please do not upload the software on this wiki, but link it as much as possible from a public repository (e.g., bitbucket, github, sourceforge) or from a stable URL on the website of your institution. If this is not possible, please contact the resources sharing working group.