FAQ
hi all..

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

*problem:*
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...


Advanced thanks...!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/python-list/attachments/20090320/f9ce460b/attachment.htm>

Search Discussions

  • Tim Chase at Mar 20, 2009 at 1:13 pm

    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
  • Stef Mientki at Mar 20, 2009 at 6:16 pm

    Murali kumar wrote:
    hi all..

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

    _problem:_
    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...


    Advanced thanks...!
    ------------------------------------------------------------------------

    --
    http://mail.python.org/mailman/listinfo/python-list
    if you are on windows,
    I would suggest Dragon Natural Speaking or Windows SAPI 5.1 (free, but
    difficult to find).
    There's Python layer written on top of the above two,
    called DragonFly,
    which uses it's own semantics and can also control the programs itself.

    cheers,
    Stef
  • Murali kumar at Mar 21, 2009 at 1:39 pm
    thanks for the reply..
    now working on cmu sphinx project..
    do u know which one
    1. cmu sphinx
    2. natural speaking
    3. windows sapi

    is best ( in accuray and speed ) for predefined vocabulary.. and worth for
    learning as well.?
    -------------- next part --------------
    An HTML attachment was scrubbed...
    URL: <http://mail.python.org/pipermail/python-list/attachments/20090321/569e7d8e/attachment.htm>
  • Tim Chase at Mar 21, 2009 at 2:08 pm

    do u know which one
    1. cmu sphinx
    2. natural speaking
    3. windows sapi

    is best ( in accuray and speed ) for predefined vocabulary.. and worth for
    learning as well.?
    For a pre-defined vocabulary, they should all be pretty good. In
    general (for non-predefined vocabularies), I've heard that NS
    beats both Sphinx and SAPI in terms of recognition quality. I
    haven't seen any comparisons between Sphinx and SAPI.

    Other considerations may also come into play:

    - do you expect all your users to have a copy of NS? Then you
    might have to look into something other than NS if they won't.
    Or perhaps NS has a developers' toolkit that allows for
    redistribution when built into your app.

    - do you expect all your users to run Windows (as I type this
    from my Linux box...)? If not, then SAPI won't be available to
    your Mac/Linux/BSD/BeOS/Amiga/whatever users.

    - do you need TTS (text-to-speech) capabilities as well? SAPI
    includes them. (there are other TTS libraries available such as
    mbrola/festival that are available for this if needed)

    - how easy is it to bind to Python? Sphinx has Python bindings
    detailed on the website. I can't speak for NS or SAPI.

    - how much time/money do you have to invest? Sphinx is
    open-source and free. SAPI is free-ish for developers, but I
    don't know if Microsoft incurs a licensing cost for distributed
    apps or other redistribution restrictions. I can't speak for
    NS-for-developers.

    Just a few thoughts,

    -tkc
  • Stef Mientki at Mar 21, 2009 at 3:10 pm

    Tim Chase wrote:
    do u know which one
    1. cmu sphinx
    2. natural speaking
    3. windows sapi

    is best ( in accuray and speed ) for predefined vocabulary.. and
    worth for
    learning as well.?
    For a pre-defined vocabulary, they should all be pretty good. In
    general (for non-predefined vocabularies), I've heard that NS beats
    both Sphinx and SAPI in terms of recognition quality. +1
    I haven't seen any comparisons between Sphinx and SAPI.

    Other considerations may also come into play:

    - do you expect all your users to have a copy of NS? Then you might
    have to look into something other than NS if they won't. Or perhaps NS
    has a developers' toolkit that allows for redistribution when built
    into your app.

    - do you expect all your users to run Windows (as I type this from my
    Linux box...)? If not, then SAPI won't be available to your
    Mac/Linux/BSD/BeOS/Amiga/whatever users.

    - do you need TTS (text-to-speech) capabilities as well? SAPI
    includes them. (there are other TTS libraries available such as
    mbrola/festival that are available for this if needed)

    - how easy is it to bind to Python? Sphinx has Python bindings
    detailed on the website. I can't speak for NS or SAPI.
    both are covered by DragonFly
    Stef
  • Murali kumar at Apr 2, 2009 at 11:49 am
    hi all..

    I tried following tools by ur advice..

    1. cmu sphinx:
    tried and managed run the demo programs.. but the accuracy is
    so bad. for that i tried for how to train the grammer. but for that i had no
    guidance.. docs give me the headache.. after 2 weeks.. i concluded that it
    will not be commercially useful for distributed application.

    2. Naturally speaking:
    downloads only provided for cost. so no try.

    3. windows sapi:
    windows provides redistributeable copies. also there are some
    python bindings available for to connect this engine. training with each
    user is easy in windows sapi ( for that i choosed this.) only limitation is
    usage within windows.

    so , concluded that using windows sapi..

    am i correct?

    if u know any best articles/links for using windows sapi from python..
    kindly give me that..



    On Sat, Mar 21, 2009 at 8:40 PM, Stef Mientki wrote:

    Tim Chase wrote:
    do u know which one
    1. cmu sphinx
    2. natural speaking
    3. windows sapi

    is best ( in accuray and speed ) for predefined vocabulary.. and worth
    for
    learning as well.?
    For a pre-defined vocabulary, they should all be pretty good. In general
    (for non-predefined vocabularies), I've heard that NS beats both Sphinx and
    SAPI in terms of recognition quality. +1
    I haven't seen any comparisons between Sphinx and SAPI.

    Other considerations may also come into play:

    - do you expect all your users to have a copy of NS? Then you might have
    to look into something other than NS if they won't. Or perhaps NS has a
    developers' toolkit that allows for redistribution when built into your app.

    - do you expect all your users to run Windows (as I type this from my
    Linux box...)? If not, then SAPI won't be available to your
    Mac/Linux/BSD/BeOS/Amiga/whatever users.

    - do you need TTS (text-to-speech) capabilities as well? SAPI includes
    them. (there are other TTS libraries available such as mbrola/festival that
    are available for this if needed)

    - how easy is it to bind to Python? Sphinx has Python bindings detailed
    on the website. I can't speak for NS or SAPI.
    both are covered by DragonFly

    Stef
    --
    http://mail.python.org/mailman/listinfo/python-list
    -------------- next part --------------
    An HTML attachment was scrubbed...
    URL: <http://mail.python.org/pipermail/python-list/attachments/20090402/fe5a2b7a/attachment.htm>
  • Tim Chase at Mar 21, 2009 at 2:09 pm

    Murali kumar wrote:
    thanks for the reply..
    now working on cmu sphinx project..
    do u know which one
    1. cmu sphinx
    2. natural speaking
    3. windows sapi

    is best ( in accuray and speed )
    ^^^^^^^
    Typo of the week...

    -tkc

Related Discussions

Discussion Navigation
viewthread | post
Discussion Overview
grouppython-list @
categoriespython
postedMar 20, '09 at 12:22p
activeApr 2, '09 at 11:49a
posts8
users3
websitepython.org

People

Translate

site design / logo © 2022 Grokbase