This paper describes a high-quality Text-to-Speech system for Spanish, based on the concatenation of diphonemes with the MBR-PSOLA algorithm. Since it was designed as a substitute of natural voice for handicapped people, it must offer a easy to hear speech, with emotional and emphatic information embedded in it. This is obtained with the prosody generator, which uses a series of phonological patterns for phonic groups and a grammatical database to vary three speech parameters: pitch, amplitude and duration. This system accepts plain text, which can be complemented with data about emotions and emphasis.
Cite as: Lacunza, F., Blanco, Y. (1998) High quality text-to-speech system in Spanish for handicapped people. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0596, doi: 10.21437/ICSLP.1998-835
@inproceedings{lacunza98_icslp,
author={Fernando Lacunza and Yolanda Blanco},
title={{High quality text-to-speech system in Spanish for handicapped people}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0596},
doi={10.21437/ICSLP.1998-835}
}