text-to-speech (207) assistive technology (157) speech synthesis (22) speech perception (3) formant synthesis (2) text-to-speech synthesis (1) language universals (1) rule-based speech synthesis (1) hybrid synthesis (1) hybrid speech synthesis (1)
Synfonica LLC is currently enhancing its text-to-speech system, Synfony, with powerful expressive capabilities. As part of this project, we are capturing how emotions are encoded and perceived in speech. Our initial focus is on English, but our system has language-universal components that will facilititate rapid development for other languages. (This work is funded in part by Small Business Innovation Research grant #R44DC014173 from the National Institute on Deafness and Other Communication Disorders of t
Ultimately, we aim to offer flexible speech output unlike anything currently available, which will be of particular benefit for users of augmentative and alternative communication technologies.
Synfony is a knowledge-based text-to-speech system that uses formant synthesis for its speech output. Formant synthesis offers a degree of control over the speech output not afforded by any other type of synthesis technology. Synfony capitalizes on this flexibility while at the same time offering substantially improved naturalness over existing formant synthesis systems.