INIGEM   23989
INSTITUTO DE INMUNOLOGIA, GENETICA Y METABOLISMO
Unidad Ejecutora - UE
congresos y reuniones científicas
Título:
Argentine Spanish segmental duration prediction
Autor/es:
HUMBERTO MAXIMILIANO TORRES; JORGE ALBERTO GURLEKIAN
Lugar:
La Plata
Reunión:
Simposio; 13th Argentine Symposium on Technology, 41 JAIIO; 2012
Institución organizadora:
SADIO
Resumen:
In this paper we model the segmental duration of Spanish spoken in Buenos Aires, considering its application in a text-to-speech system. The work was performed on two hand labeled databases. We use arti cial neural networks as predictor, and all the input features can be extracted automatically from the speech text. We experimented with a neural network for all phonemes and one neural network for phoneme. In both cases the results are very promising for the two databases used. The order of importance of input features revealed to be di erent for each of the methods tested and di erent according to the speaker style.