In this paper, we describe the development of a female voice in a Restricted-Domain Speech Synthesis System for Spanish. For the design of the database, we have used a greedyalgorithm approach that focus not only on covering a set of target phonemes, but also on mimicking the histogram of prosodic features from a larger database. For modeling the prosody, both duration and F0, we have used two Multi-Layer Perceptrons, based on our previous experience in unrestricted-domain modeling. The error normalised by the deviation is always below 0.7.
Cite as: Montero, J.M., Córdoba, R., Vallejo, J.A., Gutiérrez-Arriola, J., Enríquez, E., Pardo, J.M. (2000) Restricted-domain female-voice synthesis in Spanish: from database design to ANN prosodic modeling. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 1, 621-624
@inproceedings{montero00_icslp, author={Juan Manuel Montero and Ricardo Córdoba and José A. Vallejo and Juana Gutiérrez-Arriola and Emilia Enríquez and Juan Manuel Pardo}, title={{Restricted-domain female-voice synthesis in Spanish: from database design to ANN prosodic modeling}}, year=2000, booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)}, pages={vol. 1, 621-624} }