Expressive speech style transformation: Voice quality and prosody modification using a harmonic plus noise model

Carlos Monzo, Àngel Calzada, Ignasi Iriondo, Joan Claudi Socoró

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

4 Cites (Scopus)

Resum

This paper proposes an approach to transform speech from a neutral style into other expressive styles using both prosody and voice quality (VoQ). The main aim is to validate the usefulness of VoQ in the enhancement of expressive synthetic speech. A Harmonic plus Noise Model (HNM) is used to modify speech following a set of rules extracted from an expressive speech corpus with five categories (neutral, happy, sensual, aggressive and sad). Finally, modified speech utterances were used to perform a perceptual test. These results indicate that listeners prefer prosody together with VoQ transformation instead of only prosody modification.

Idioma originalAnglès
Títol de la publicació5th International Conference on Speech Prosody 2010
EditorInternational Speech Communications Association
ISBN (electrònic)9780000000002
Estat de la publicacióPublicada - 2010
Esdeveniment5th International Conference on Speech Prosody: Every Language, Every Style, SP 2010 - Chicago, United States
Durada: 10 de maig 201014 de maig 2010

Sèrie de publicacions

NomProceedings of the International Conference on Speech Prosody
ISSN (imprès)2333-2042

Conferència

Conferència5th International Conference on Speech Prosody: Every Language, Every Style, SP 2010
País/TerritoriUnited States
CiutatChicago
Període10/05/1014/05/10

Com citar-ho