Multi-domain text-to-speech synthesis by automatic text classification

Francesc Alías*, Joan Claudi Socoró, Xavier Sevillano, Ignasi Iriondo, Xavier Gonzalvo

*Autor correspondiente de este trabajo

Producción científica: Capítulo del libroContribución a congreso/conferenciarevisión exhaustiva

1 Cita (Scopus)

Resumen

This paper describes a multi-domain text-to-speech (MD-TTS) synthesis strategy for generating speech among different domains and so increasing the flexibility of high quality TTS systems. To that effect, the MD-TTS introduces a flexible TTS architecture that includes an automatic domain classification module, which allows MD-TTS systems to be implemented by different synthesis strategies and speech corpus typologies. In this work, the performance of a corpus-based MD-TTS system is subjectively validated by means of several perceptual tests.

Idioma originalInglés
Título de la publicación alojadaINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
EditorialInternational Speech Communication Association
Páginas1304-1307
Número de páginas4
ISBN (versión impresa)9781604234497
EstadoPublicada - 2006
EventoINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP - Pittsburgh, PA, Estados Unidos
Duración: 17 sept 200621 sept 2006

Serie de la publicación

NombreINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
Volumen3

Conferencia

ConferenciaINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
País/TerritorioEstados Unidos
CiudadPittsburgh, PA
Período17/09/0621/09/06

Huella

Profundice en los temas de investigación de 'Multi-domain text-to-speech synthesis by automatic text classification'. En conjunto forman una huella única.

Citar esto