It currently does not support VoiceXML. In fact, you need something _else_ that does that, like a voice browser, which sends the right information about grammars, etc to the recognition engine at the right times and also controls the speech output to a synthesizer. So VoiceXML is really above the component technology level and more at the dialog management level.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I'm looking through sphinx docs and these discussion groups and it seems that sphinx is suitable only for dictation and not for grammar based speech recognition (Required by voicexml browsers). Is that correct? Does anybody knows open source speech recognition engine that uses grammars?
Thanks,
Leonardo.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
[Sorry I'm new to Sphinx]
I was looking for an open source VoiceXML server.
Does Sphinx have it's own markup language or
does it support VoiceXML?
It currently does not support VoiceXML. In fact, you need something _else_ that does that, like a voice browser, which sends the right information about grammars, etc to the recognition engine at the right times and also controls the speech output to a synthesizer. So VoiceXML is really above the component technology level and more at the dialog management level.
I'm looking through sphinx docs and these discussion groups and it seems that sphinx is suitable only for dictation and not for grammar based speech recognition (Required by voicexml browsers). Is that correct? Does anybody knows open source speech recognition engine that uses grammars?
Thanks,
Leonardo.