Speech synthesis based on the Multiband Resynthesis OverLap-Add (MBROLA) algorithm produces high quality speech without requiring too much effort to design the diphone database, and using a low computational power. The main drawback of this algorithm is the slightly metallic sound or buzziness that can be perceived on voiced segments. We are working on a speech synthesizer based on the MBROLA algorithm, and trying to improve its speech quality by means of on an enhanced phase control strategy.
Cite as: Etxebarria, B., Hernáez, I., Madariaga, I., Navas, E., Rodríguez, J.C., Gándara, R. (1999) Improving quality in a speech synthesizer based on the MBROLA algorithm. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2299-2302, doi: 10.21437/Eurospeech.1999-501
@inproceedings{etxebarria99_eurospeech,
author={B. Etxebarria and I. Hernáez and I. Madariaga and E. Navas and J. C. Rodríguez and R. Gándara},
title={{Improving quality in a speech synthesizer based on the MBROLA algorithm}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2299--2302},
doi={10.21437/Eurospeech.1999-501}
}