The objective of this paper is to investigate whether prosodic phrase breaks are specific to a speaker, and if so, propose a mechanism of learning speaker-specific phrase breaks from the speech database. Another equally important aspect dealt in this work is to demonstrate the usefulness of these speaker-specific phrase breaks for a text-to-speech system. Experiments are carried out on two different English voices as well as on a Telugu voice, and it is shown that speaker-specific phrase breaks improves duration as well as spectral quality of synthetic speech.
Index Terms: speech synthesis, speaker-specific phrase breaks, semi-supervised learning
Cite as: Prahallad, K., Raghavendra, E.V., Black, A.W. (2010) Learning speaker-specific phrase breaks for text-to-speech systems. Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7), 162-166
@inproceedings{prahallad10b_ssw,
author={Kishore Prahallad and E. Veera Raghavendra and Alan W. Black},
title={{Learning speaker-specific phrase breaks for text-to-speech systems}},
year=2010,
booktitle={Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7)},
pages={162--166}
}