speech recognition help

Tim Chase python.list at tim.thechases.com
Fri Mar 20 14:13:27 CET 2009


> I want* to add speech recognition *to my application for *disabled persons*.
> (running in python 2.6 with wxpython 2.8.9..)
> 
> *problem:*

too many asterisks? ;-)

> actually i have some buttons scanned one by one.. button name is 'add' and
> if i tell 'add' then add button click event must be performed..
> 
> For that i need the conversion of *speech to text.*
> 
> Tell me the right advice and necessary links to implement this...

Usually this is relegated to utility software -- Dragon Naturally 
Speaking[1] is one of the most popular.  They tend to do more 
reliably (higher recognition rates) with fixed vocabularies for 
issuing commands than in free-form dictation.

There's the open-source CMU Sphinx project[2] which may allow you 
to more easily interact with it programatically via an API.  On 
my Debian box, it's just an apt-get away[3].  Note that this is 
*different* from the python-sphinx documentation package just 
mentioned in a nearby thread on c.l.p

There's documentation[4] on connecting Python + Sphinx2 that may 
be of assistance.

-tkc



[1]
http://www.nuance.com/naturallyspeaking/

[2]
http://cmusphinx.org/

[3]
apt-cache search sphinx2

[4]
http://sphinx.subwiki.com/sphinx/index.php/Sphinx3_python_quickstart



More information about the Python-list mailing list