Linguistic features weighting for a Text-To-Speech system without prosody model

Vincent Colotte 1 Richard Beaufort 2
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper presents a Non-Uniform Units selection-based Text-To-Speech synthesizer. Nowadays, systems use prosodic models that do not allow the prosody to vary as far as we should hope, involving a listening comfort degradation. Our system has the advantage to avoid the using of prosodic model. Speech units selection builds its features set exclusively from the linguistic information generated by the natural language analysis. We also present an original method to automatically weight these features. Therefore, selected units are not restricted by a predetermined prosody. With only using linguistic features, we obtain a various prosody and the units concatenation is performed without resort to heavy signal processing
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00012561
Contributor : Vincent Colotte <>
Submitted on : Wednesday, November 23, 2005 - 4:48:24 PM
Last modification on : Thursday, January 11, 2018 - 6:19:56 AM

Identifiers

  • HAL Id : hal-00012561, version 1

Collections

Citation

Vincent Colotte, Richard Beaufort. Linguistic features weighting for a Text-To-Speech system without prosody model. 2005, pp.2549--2552. ⟨hal-00012561⟩

Share

Metrics

Record views

336