Use this identifier to quote or link this document: http://hdl.handle.net/2072/374110

Title:	Voice quality modelling for expressive speech synthesis
Author:	Monzo Sánchez, Carlos; Iriondo Sanz, Ignasi; Socoró Carrié, Joan Claudi
Other authors:	Universitat Ramon Llull. La Salle; Universitat Oberta de Catalunya. Computer Science, Multimedia and Telecomunications Studies
Abstract:	This paper presents the perceptual experiments that were carried out in order to validate the methodology of transforming expressive speech styles using voice quality (VoQ) parameters modelling, along with the well-known prosody (, duration, and energy), from a neutral style into a number of expressive ones. The main goal was to validate the usefulness of VoQ in the enhancement of expressive synthetic speech in terms of speech quality and style identification. A harmonic plus noise model (HNM) was used to modify VoQ and prosodic parameters that were extracted from an expressive speech corpus. Perception test results indicated the improvement of obtained expressive speech styles using VoQ modelling along with prosodic characteristics
Publication date:	2014-01
Subject (UDC):	81 - Lingüística y lenguas
Subject(s):	Parla
Rights:	L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons:http://creativecommons.org/licenses/by/4.0/ © L'autor/a
Pages:	13 p.
Document type:	Article Article - Published version
DOI:	https://doi.org/10.1155/2014/627189
Published by:	Hindawi Publishing Corporation
Publish at:	The Scientific World Journal. 2014
Share:

Full text files in this document

Show full item record