Speech and Vision Lab

  • Increase font size
  • Default font size
  • Decrease font size
Home Publications
Learning Speaker-Specific Phrase Breaks for Text-to-Speech Systems
Research Area: Speech Synthesis Year: 2010
Type of Publication: In Proceedings Keywords: speech synthesis, speaker specific phrase breaks, semi supervised learning
Authors: Kishore S. Prahallad, Veera Raghavendra Elluru, A. W. Black  
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.
Digital version