Unit Selection Cost Function Exploration Using an A* based Text-to-Speech System

David Guennec 1 Damien Lolive 1
1 EXPRESSION - Expressiveness in Human Centered Data/Media
UBS - Université de Bretagne Sud, IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : Speech synthesis systems usually use the Viterbi algorithm as a basis for unit selection, while it is not the only possible choice. In this paper, we study a speech synthesis system relying on the A* algorithm, which is a general pathfinding strategy developing a graph rather than a lattice. Using state of the art techniques, we propose and analyze different selection strategies and evaluate them using a subjective evaluation on the N-best paths returned. The best strategy achieves a MOS score of 3.29 (±0.18). More interesting, the proposed system enables an in-depth analysis of unit selection.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-01133321
Contributor : Expression Irisa <>
Submitted on : Thursday, March 19, 2015 - 9:23:44 AM
Last modification on : Thursday, November 15, 2018 - 11:58:49 AM

Identifiers

  • HAL Id : hal-01133321, version 1

Citation

David Guennec, Damien Lolive. Unit Selection Cost Function Exploration Using an A* based Text-to-Speech System. International Conference on Text, Speech and Dialogue (TSD), Sep 2014, Brno, Czech Republic. ⟨hal-01133321⟩

Share

Metrics

Record views

739