The World Wide Web Consortium (W3C) has announced plans to develop the next generation of VoiceXML. The new version will include a feature — termed “speaker verification” — to allow for the verification of callers based on their voice print. This will enhance the security of voice applications, and extend their usefulness in supporting sensitive transactions.
For some background on speaker verification, check out this piece written for the VoiceXML Review by Ken Rehor, the new Chairman of the VoiceXML Forum. If you want to play around with speaker verification, you can check out the extension available on the BeVocal platform. (Keep in mind, however, that the implementation of speaker verification in VoiceXML 3.0 may differ from BeVocal’s implementation.)
As part of the same announcement, the W3C also announced that it will work to further internationalize VoiceXML and its sister specifications to include Mandarin Chinese.