The Seventh ISCA Tutorial and Research Workshop on Speech Synthesis Kyoto, Japan September 22-24, 2010

Learning Speaker-Specific Phrase Breaks for Text-to-Speech Systems

Kishore Prahallad (1,2), E. Veera Raghavendra (1), Alan W. Black (2)

(1) International Institute of Information Technology, Hyderabad, India.
(2) Language Technologies Institute, Carnegie Mellon University, USA.

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

Full Paper

Bibliographic reference.  Prahallad, Kishore / Raghavendra, E. Veera / Black, Alan W. (2010): "Learning speaker-specific phrase breaks for text-to-speech systems", In SSW7-2010, 162-166.