Admissible stopping in viterbi beam search for unit selection in concatenative speech synthesis

Corpus-based concatenative speech synthesis is very popular these days due to its highly natural speech quality. The amount of computation required in the run time, however, is often quite large and various approaches have been proposed for reducing this runtime computation. In this paper, we propose early stopping schemes for Viterbi beam search in the unit selection, with which we can stop early in the local Viterbi maximization for each unit as well as in the exploration of candidate units for a given target. It takes advantage of the fact that the space of the acoustic parameters of the database units is closed and certain upper bounds of the concatenation scores can be precomputed. The proposed method for early stopping is admissible in that it does not change the result of the Viterbi beam search if the upper bounds are properly computed. Experiments show that the proposed methods of admissible stopping effectively reduce the amount of computation required in the Viterbi beam se...

• Type: Conference
• Year: 2008
• Where: ICASSP
• Authors: Shinichi Sakai, Tatsuya Kawahara, Shun Nakamura
• Keywords: Early Stopping, ICASSP 2008, Local Viterbi Maximization, Signal Processing, Viterbi Beam Search