Browsing by Author "Gonzalvo Fructuoso, Xavier"
Now showing items 1-5 of 5
-
High quality Spanish restricted-domain TTSoriented to a weather forecast application
Alías Pujol, Francesc; Iriondo Sanz, Ignasi; Formiga Fanals, Lluís; Gonzalvo Fructuoso, Xavier; Monzo Sánchez, Carlos; Sevillano Domínguez, Xavier (2005-09-04)A restricted domain text-to-speech system oriented to a weatherforecast application is presented. This TTS system is embed-ded in a multimedia interactive service accessible from differ-ent media, such ... -
HMM-based Spanish speech synthesis using CBR as F0 estimator
Gonzalvo Fructuoso, Xavier; Iriondo Sanz, Ignasi; Socoró Carrié, Joan Claudi; Alías Pujol, Francesc; Monzo Sánchez, Carlos (2007-05)Hidden Markov Models based text-to-speech (HMM-TTS) syn thesis is a technique for generating speech from trained statisti cal models where spectrum, pitch and durations of basic speech units are modelled ... -
Linguistic and Mixed Excitation Improvements on a HMM-based speech synthesis for Castilian Spanish
Gonzalvo Fructuoso, Xavier; Socoró Carrié, Joan Claudi; Iriondo Sanz, Ignasi; Monzo Sánchez, Carlos; Martínez Marroquín, Elisa (Proceedings of the 6th ISCA Workshop on Speech Synthesis, 2007-08)HiddenMarkov Models based text-to-speech(HMM-TTS)synthesis is one of the techniques for generating speech from trained statistical models where spectrum and prosody of basic speech units are modelled ... -
Local minimum generation error criterion for hybrid HMM speech synthesis
Gonzalvo Fructuoso, Xavier; Gutkin, Alexander; Socoró Carrié, Joan Claudi; Iriondo Sanz, Ignasi; Taylor, Paul (2009-09)This paper presents an HMM-driven hybrid speech synthesis approach in which unit selection concatenative synthesis is used to improve the quality of the statistical system using a Local Minimum Generation ... -
Multi-domain Text-to-Speech Synthesis by Automatic Text Classification
Alías Pujol, Francesc; Socoró Carrié, Joan Claudi; Sevillano Domínguez, Xavier; Iriondo Sanz, Ignasi; Gonzalvo Fructuoso, Xavier (2006-09-17)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 ...