Hello,

I am trying to do simultaneous speech recognition and TTS via mod_unimrcp using detect_speech and speak.

What I want to achieve is to enable a user to say something like "shut up" to stop TTS rather than using standard barge-in to stop TTS.

When I spoke something during playing a sentence, I noticed there were some recognition results from FS log,
but my ESL app didn't get any DETECTED_SPEECH or BEGIN_SPEAKING events.

Has any body had similar experiences before?

From Arsen Chaloyan's comments at 11 July 2011:

"If I'm not mistaken, neither Asterisk nor FreeSWITCH are currently
capable to play a TTS prompt while making a recognition. However, I
don't see any conceptual problem here. This is somewhat not
implemented yet for those open source projects. Other UniMRCP based
implementations do this job very well."

I am wondering if the current mod_unimrcp does not support concurrent recognition and tts
or if I am not using it properly?


Thanks!

Xing

---

Sunday Times Scottish University of the Year 2011-2013
Top in the UK for student experience
Fourth university in the UK and top in Scotland (National Student Survey 2012)

We invite research leaders and ambitious early career researchers to join us in leading and driving research in key inter-disciplinary themes. Please see www.hw.ac.uk/researchleaders for further information and how to apply.

Heriot-Watt University is a Scottish charity registered under charity number SC000278.