Multi-domain Text-to-Speech Synthesis by Automatic Text Classification

All of RECERCAT

Use this identifier to quote or link this document: http://hdl.handle.net/2072/376272

Title:	Multi-domain Text-to-Speech Synthesis by Automatic Text Classification
Author:	Alías Pujol, Francesc; Socoró Carrié, Joan Claudi; Sevillano Domínguez, Xavier; Iriondo Sanz, Ignasi; Gonzalvo Fructuoso, Xavier
Other authors:	Universitat Ramon Llull. La Salle
Abstract:	This paper describes a multi-domain text-to-speech (MD-TTS)synthesis strategy for generating speech among different domainsand so increasing the flexibility of high quality TTS systems. Tothat effect, the MD-TTS introduces a flexible TTS architecture thatincludes an automatic domain classification module, which allowsMD-TTS systems to be implemented by different synthesis strate-gies and speech corpus typologies. In this work, the performanceof a corpus-based MD-TTS system is subjectively validated bymeans of several perceptual tests
Publication date:	2006-09-17
Subject(s):	Parla Processament de la parla
Rights:	© L'autor/a. Tots els drets reservats
Pages:	4 p.
Document type:	Article Article - Published version
Published by:	Ninth International Conference on Spoken Language Processing. INTERSPEECH 2006
Share:

Files	Size	Format	Description
aliasICSLP06b.pdf	93.85 KB	PDF	INTERSPEECH2006