Making Sense of Variations: Introducing Alternatives in Speech Synthesis

Christophe Veaux, Nicolas Obin, Pierre Lanchantin

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper addresses the use of speech alternatives to enrich speech synthesis systems. Speech alternatives denote the variety of strategies that a speaker can use to pronounce a sentence - depending on pragmatic constraints, speaking style, and specific strategies of the speaker. During the training, symbolic and acoustic characteristics of a unit-selection speech synthesis system are statistically modelled with context-dependent para-metric models (GMMs/HMMs). During the synthesis, symbo-lic and acoustic alternatives are exploited using a GENERALIZED VITERBI ALGORITHM (GVA) to determine the sequence of speech units used for the synthesis. Objective and subjective evaluations supports evidence that the use of speech alterna-tives significantly improves speech synthesis over conventional speech synthesis systems.
Original languageEnglish
Title of host publicationProceedings of the 6th International Conference on Speech Prosody 2012
PublisherTongji University Press
ISBN (Print)978-7-5608-4869-3
Publication statusPublished - May 2012
EventSpeech Prosody, 6th International Conference - Shanghai, China
Duration: 22 May 201225 May 2012


ConferenceSpeech Prosody, 6th International Conference


  • speech synthesis
  • speech prosody
  • speech alternatives


Dive into the research topics of 'Making Sense of Variations: Introducing Alternatives in Speech Synthesis'. Together they form a unique fingerprint.

Cite this