[Freeswitch-users] mod_rtmp audio codecs issues for speech recognition?

x.liu x.liu at hw.ac.uk
Wed Aug 15 15:34:57 MSD 2012


Hello,

I am trying the FS sample Flex client for TTS and speech recognition.
The TTS sounds OK. I use Nuance MRCP v1 server with Nuance recognizer 9.

The problem is that I hardly get the recognition result,only 
occasionally I got some simple words output like "repeat", "ok" which 
were not I said.
The whole recognition setup works well when I use a telephone line but 
basically not work by using the flex client from a web broswer.
The recorded voices in FS which were sent from the web browser via the 
flash rtmp sound fine.

I guess it may be the audio codec issues. The flash rtmp uses Speex. My 
mrcp profile specifies the codecs as "PCMU PCMA L16/96/8000"

Is there a way to automatically convert the Speex audio to the mrcp 
required formats during calling the system?
Or what should I look at to get the proper speech recognition via the 
flash rtmp?

Many thanks!

Xing



-- 
Heriot-Watt University is the Sunday Times
Scottish University of the Year 2011-2012

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.




Join us at ClueCon 2011 Aug 9-11, 2011
More information about the FreeSWITCH-users mailing list