RE: Speech To SSML

Voice Browser Working Group,

PROSOTRAN and related technologies have an applicability to the synthesis and recognition of mathematical and scientific notation (http://lists.w3.org/Archives/Public/www-voice/2012AprJun/0003.html).

Grammars can be described to recognize spoken mathematical and scientific notation in enhanced ways utilizing descriptions of multi-tiered prosodic data.  Multi-tiered prosodic output could be topical to discussions about SRGS and SISR.  Prosodic data from speech recognition components can enhance approaches to natural language systems, affective computing, and dialogue systems.

Speech-to-XML, speech-to-SSML, and related technologies, including tools where prosodic spoken audio can be roundtripped through SSML, can convenience numerous research and development processes.



Kind regards,
Adam Sobieski