Inproceedings,

HMM-Based Hierarchical Unit Selection Combining Kullback-Leibler Divergence with Likelihood Criterion

, and .
Proceedings of the 2007 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4, page 1245-1248. Honolulu, HI, USA, (April 2007)
DOI: 10.1109/ICASSP.2007.367302

Abstract

This paper presents a hidden Markov model (HMM) based unit selection method using hierarchical units under statistical criterion. In our previous work we tried to use frame sized speech segments and maximum likelihood criterion to improve the performance of traditional concatenative synthesis system using phone sized units and cost function criterion. In this paper, hierarchical units which consist of phone level units and frame level units are adopted to achieve better balance between the coverage rate of candidate unit and the number of concatenation points during synthesis. Besides, Kullback-Leibler divergence (KLD) between candidate and target phoneme HMMs is introduced as a part of the final criterion for unit selection. The listening result proves that these two approaches can improve the performance of synthetic speech effectively.

Tags

Users

  • @m-toman
  • @dblp

Comments and Reviews