Very fast unit selection using Viterbi search with zero-concatenation-cost chains
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 2569-2573
Abstract
This paper introduces a very fast heuristic search algorithm for unit-selection speech synthesis. The algorithm modifies commonly used Viterbi search framework by introducing zero-concatenation-cost (ZCC) chains of unit candidates that immediately neighbored in a source speech corpus. ZCC chains are preferred as they represent perfect speech segment concatenations (so there is no need to compute concatenation costs inside the chains) unless a so-called target specification is violated. The number of ZCC chains is reduced based on statistics calculated upon the synthesis of a large number of utterances. ZCC chains are then combined with single unit candidates to fill possible gaps in the sequence of candidates. The proposed method reduces the computational load of a unit selection system up to hundreds of times. According to listening tests, the quality of synthetic speech was not deteriorated.Keywords
This publication has 8 references indexed in Scilit:
- Experiments on Reducing Footprint of Unit Selection TTS SystemLecture Notes in Computer Science, 2013
- Enhancements of viterbi search for fast unit selection synthesis2010
- A statistical method for database reduction for embedded unit selection speech synthesisInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008
- Recording and Annotation of Speech Corpus for Czech Unit Selection Speech SynthesisLecture Notes in Computer Science, 2007
- Current State of Czech Text-to-Speech System ARTIC2006
- A Text-to-Speech Platform for Variable Length Optimal Unit Searching Using Perception Based Cost FunctionsInternational Journal of Speech Technology, 2003
- Rapid unit selection from a large speech corpus for concatenative speech synthesis1999
- Unit selection in a concatenative speech synthesis system using a large speech database1996