Open-Source Speech Recognition Toolkits
Tuesday, 26th August, 2014
Here’s a list of FOSS and FOSS-ish ASR toolkits: url, license and rough activity dates, and maybe the odd comment.
Apart from Sphinx4, which is written in The Java Programming Language, all of these are written in C/C++.
Kaldi looks the most interesting and mature. I’d also like to have more of a look at Bavieca, GMTK and TLK.
Have I missed any?
-
Bavieca
Apache 2.0
2012-2013 -
GMTK
Open Software License v. 3.0
2011? -
HTK
Weird license:- http://htk.eng.cam.ac.uk/docs/license.shtml
- owned by Microsoft
- any use, no redistribution
- i.e., can use to train but cannot distribute recogniser: must distribute separate recogniser (eg Julius)
Latest version is 3.4.1, 2009
-
iAtros
GPL
2008?unclear documentation
unclear if HTK required
designed for recognition of speech and handwriting -
Kaldi
Apache 2.0
Current (last sf update 2014-08-11) -
RASR
Non-commercial use only
2007-11? -
SCARF
Non-Commercial Use Only
2010-11? -
SPRAAK
Free for non-commercial use only; commercial license request & pay
2009-10 -
Sphinx
BSD
Sphinx4 (java) is current
Sphinx3 (C/C++) is unmaintained -
TLK
Apache 2.0
2013 & current