Robust automatic speech recognition with missing and unreliable acoustic data
Speech Communication
Speech Synthesis and Recognition
Speech Synthesis and Recognition
Computers & Mathematics with Applications
CanSpeak: a customizable speech interface for people with dysarthric speech
ICCHP'10 Proceedings of the 12th international conference on Computers helping people with special needs: Part I
Hi-index | 0.00 |
This paper describes an approach to the development of a voice-input voice-output communication aid (VIVOCA) for people with disordered or unintelligible speech, initially concentrating on people with moderate to severe dysarthria. The VIVOCA is intended to recognize and interpret an individual's disordered speech and speak out an equivalent message in clear synthesized speech. User consultation suggests that such a device would be acceptable and would be useful in communication situations where speed and intelligibility are crucial. Speech recognition techniques will build on previously successful development of speech-based home control interfaces, and various methods for speech ‘translation' are being evaluated