Efficient interactive weight tuning for tts synthesis: Reducing user fatigue by improving user consistency

Francesc Alías, Xavier Llorà, Lluís Formiga, Kumara Sastry, David E. Goldberg

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

9 Cites (Scopus)

Resum

The quality of corpus-based text-to-speech systems depends on the accuracy of the unit selection process, which in turn relies on the cost function definition. This function should map the user perceptual preference when selecting synthesis units, which is a very difficult task. This paper continues our previous work on fusing the human judgements with the cost function by means of interactive weight tuning. The application of active interactive genetics algorithms mitigates user fatigue by improving user consistency. As a result, the obtained weights generate more natural synthetic speech when compared to previous objective and subjective proposals.

Idioma originalAnglès
Títol de la publicació2006 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings
PàginesI865-I868
Estat de la publicacióPublicada - 2006
Esdeveniment2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006 - Toulouse, France
Durada: 14 de maig 200619 de maig 2006

Sèrie de publicacions

NomICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volum1
ISSN (imprès)1520-6149

Conferència

Conferència2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006
País/TerritoriFrance
CiutatToulouse
Període14/05/0619/05/06

Fingerprint

Navegar pels temes de recerca de 'Efficient interactive weight tuning for tts synthesis: Reducing user fatigue by improving user consistency'. Junts formen un fingerprint únic.

Com citar-ho