The UK Home Automation Archive

Archive Home
Group Home
Search Archive


Advanced Search

The UKHA-ARCHIVE IS CEASING OPERATIONS 31 DEC 2024


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Fwd: [misterhouse-users] Linux Speech Recognition


  • To: ukha_d@xxxxxxx
  • Subject: Fwd: [misterhouse-users] Linux Speech Recognition
  • From: Stuart Grimshaw <stuart@xxxxxxx>
  • Date: Tue, 13 Aug 2002 16:48:35 +0100
  • Mailing-list: list ukha_d@xxxxxxx; contact ukha_d-owner@xxxxxxx
  • Reply-to: ukha_d@xxxxxxx

This appeared on the Misterhouse mailing list ... have a look at the webpage
...

"SphinxTrain, an environment for building acoustic models for the CMU Sphinx2
and Sphinx3 engines. With enough data (and effort), you can create acoustic
models for any language, task, or channel conditions that will allow the
run-time engines to recognize the speech. Sphinx, plus an acoustic model,
plus a language model gives you everything you need to build systems that use
speech recognition. "

Kind of suggests you can create speach recognition for even poor conditions.

----------  Forwarded Message  ----------

Subject: [misterhouse-users] Linux Speech Recognition
Date: Tue, 13 Aug 2002 07:41:30 -0700
From: Clint Dimick <clint@xxxxxxx>
To: misterhouse-users@xxxxxxx
In light of the now-unavailable ViaVoice SDK files, I hunted around for
a potential alternative to speech recognition for my Linux MH platform.
The MH docs. mention the "Sphinx" project at Carnegie Mellon University,
and so far I have been impressed with the results.  More information can
be found at: http://fife.speech.cs.cmu.edu/speech/sphinx/   The project
group even has a test system running at 1-877-268-7526 which will provide
real flight information.  Impressive!

For us Debian GNU/Linux folks, "apt-get install sphinx2" will get the
necessary files installed.  Downloads are available for other platforms
at http://sourceforge.net/projects/cmusphinx/  Has anyone else been
experimenting with this system?

This leads me to a related question: how do those of you who are using
speech recognition in your automation projects configure your mic. setup
throughout the house?  Does your system "know" which room(s) the voice
commands come from?  How do you determine this - motion sensor activity
that coincides with speed commands, multiple mic. inputs on the server?

      - Clint


-------------------------------------------------------
This sf.net email is sponsored by: Dice - The leading online job board
for high-tech professionals. Search and apply for tech jobs today!
http://seeker.dice.com/seeker.epl?rel_code=31
________________________________________________________
To unsubscribe from this list, go to:
http://sourceforge.net/mail/?group_id=1365

-------------------------------------------------------



Yahoo! Groups Sponsor
ADVERTISEMENT

For more information: http://www.automatedhome.co.uk
Post message: ukha_d@xxxxxxx
Subscribe:  ukha_d-subscribe@xxxxxxx
Unsubscribe:  ukha_d-unsubscribe@xxxxxxx
List owner:  ukha_d-owner@xxxxxxx

Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.

Home | Main Index | Thread Index

Comments to the Webmaster are always welcomed, please use this contact form . Note that as this site is a mailing list archive, the Webmaster has no control over the contents of the messages. Comments about message content should be directed to the relevant mailing list.