I would like to add a VAD layer to the sphinx 3 live recognizer to detect both beginning and end of utterances. There is a VAD library for pocketsphinx, and also a couple of VAD implementations in the Olympus project. Do you have any feedback on this problem? Any advice on what to start with would be extremely useful.
Thanks!
Sylvain
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
I would like to add a VAD layer to the sphinx 3 live recognizer to detect both beginning and end of utterances. There is a VAD library for pocketsphinx, and also a couple of VAD implementations in the Olympus project. Do you have any feedback on this problem? Any advice on what to start with would be extremely useful.
Thanks!
Sylvain
Better, use pocketsphinx.