W3C home > Mailing lists > Public > public-xg-htmlspeech@w3.org > October 2011

statistical models discussion

From: Deborah Dahl <dahl@conversational-technologies.com>
Date: Wed, 26 Oct 2011 21:32:06 -0400
To: <public-xg-htmlspeech@w3.org>
Message-ID: <014e01cc9448$3d836840$b88a38c0$@conversational-technologies.com>
If you happen to be around TPAC on Tuesday afternoon, you might be
interested in a discussion we're having during the Multimodal Interaction
Working Group on multimodal use cases for standardizing statistical language
models and possible updates to SRGS. A multimodal environment makes it
possible to do things like display speech recognition results and it makes
it much easier to get user corrections than a voice-only environment.
Consequently, I think that statistical recognition has some interesting use
cases in a multimodal setting. Please let me know if you'd like to join the
discussion and aren't already in the MMIWG. I plan to schedule this for
after the break on Tuesday afternoon. 
Received on Thursday, 27 October 2011 01:32:45 UTC

This archive was generated by hypermail 2.3.1 : Tuesday, 6 January 2015 20:16:50 UTC