CMU Sphinx is one of the most popular speech recognition applications for Linux and it can correctly capture words. it also gives the developers the ability to build speech systems, interact with voice and build something unique and useful.
One of the good things about Sphinx is that it comes with precompiled binaries for Ubuntu and derivatives. Additionally, it has many language models , so you can use it for many human languages.
CMU Sphinx toolkit has a number of packages for different tasks and applications. It’s sometimes confusing what to choose. To cleanup, here is the list
- Pocketsphinx — recognizer library written in C.
- Sphinxbase — support library required by Pocketsphinx
- Sphinx4 — adjustable, modifiable recognizer written in Java
- CMUclmtk — language model tools
- Sphinxtrain — acoustic model training tools
You can download CMU Sphinx Toolkit from sourceforge
For installation of Sphinx 4 check the installation instructions in the wiki page.
– For Ubuntu and LinuxMint:
There is a PPA available for CMU Sphinx, but seems that is not updated to work in Ubuntu 10.10 maverick Meerkat, at least for me didn`t work.The PPA is the following
Or check the Launchpad :https://launchpad.net/~dhuggins/+archive/cmusphinx
– If you want to learn how to use Sphinx to recognize speech, check the wiki page
– If you are a developer, this link can be interesing for you : CMUSphinx Tutorial For Developers