Unit Selection Cost Function Exploration Using an A* based Text-to-Speech System - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

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

David Guennec
  • Function : Author
  • PersonId : 955117

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.
No file

Dates and versions

hal-01133321 , version 1 (19-03-2015)

Identifiers

  • HAL Id : hal-01133321 , version 1

Cite

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⟩
410 View
0 Download

Share

Gmail Facebook X LinkedIn More