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?
Open Software License v. 3.0
- 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
unclear if HTK required
designed for recognition of speech and handwriting
Current (last sf update 2014-08-11)
Non-commercial use only
Non-Commercial Use Only
Free for non-commercial use only; commercial license request & pay
Sphinx4 (java) is current
Sphinx3 (C/C++) is unmaintained
2013 & current