4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Whistler: A Trainable Text-to-Speech System

X. D. Huang, Alex Acero, J. Adcock, H. W. Hon, J. Goldsmith, J. Liu, Mike Plumpe

Microsoft Corporation, Redmond, WA, USA

We introduce Whistler, a trainable Text-to-Speech (TTS) system, that automatically learns the model parameters from a corpus. Both prosody parameters and concatenative speech units are derived through the use of probabilistic learning methods that have been successfully used for speech recognition. Whistler can produce synthetic speech that sounds very natural and resembles the acoustic and prosodic characteristics of the original speaker. The underlying technologies used in Whistler can significantly facilitate the process of creating generic TTS systems for a new language, a new voice, or a new speech style.

Full Paper

Bibliographic reference.  Huang, X. D. / Acero, Alex / Adcock, J. / Hon, H. W. / Goldsmith, J. / Liu, J. / Plumpe, Mike (1996): "Whistler: a trainable text-to-speech system", In ICSLP-1996, 2387-2390.