Making Sense of Variations: Introducing Alternatives in Speech Synthesis

Nicolas Obin (1) , Christophe Veaux (1, 2) , Pierre Lanchantin (1, 3)

1 STMS - Sciences et Technologies de la Musique et du Son
2 CSTR - The Centre for Speech Technology Research [Edinburgh]
3 CAM - University of Cambridge [UK]

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 parametric models (GMMs/HMMs). During the synthesis, symbolic 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 alternatives significantly improves speech synthesis over conventional speech synthesis systems.

Mots clés: speech synthesis; speech prosody; speech alternatives

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]; Applications [stat.AP]; Linguistique

Nicolas Obin, Christophe Veaux, Pierre Lanchantin. Making Sense of Variations: Introducing Alternatives in Speech Synthesis. Speech Prosody, May 2012, Shanghai, China. ⟨hal-00663837⟩