Hello, Question for developers: what is the asterisk way to integrate with ASR (speech recognition)? Question to the community: has someone done anything in this direction? On the first glance that shouldn't be too hard. One part is delivering audio to the engine (for example, main ASR players Nuance and Speechworks will be happy with RTP) - can be done via RTP forking. The other part is stopping the prompt when speech is detected (barge-in implementation). One more thing is adding the related commands to agi. Any comments are welcome. Thank you. Alex Zarubin -------------- next part -------------- An HTML attachment was scrubbed... URL: http://lists.digium.com/pipermail/asterisk-users/attachments/20030618/4dc30c09/attachment.htm
Steven Critchfield
2003-Jun-18 15:45 UTC
[Asterisk-Users] Integration with external ASR engines
On Wed, 2003-06-18 at 17:18, Alex Zarubin wrote:> Hello, > > Question for developers: what is the asterisk way to integrate with > ASR (speech recognition)? > Question to the community: has someone done anything in this > direction? > > On the first glance that shouldn't be too hard. One part is delivering > audio to the engine (for example, > main ASR players Nuance and Speechworks will be happy with RTP) - can > be done via RTP forking. > The other part is stopping the prompt when speech is detected > (barge-in implementation). One more > thing is adding the related commands to agi.Check out eagi. Eagi is extended to provide audio data to the agi app at STDERR+1 file handle. There is a example of it in the CVS repository already of hooking asterisk up to a speech rec system. -- Steven Critchfield <critch@basesys.com>