Minimum generation error criterion considering global/local variance for HMM-based speech synthesis

Due to the inconsistency between the maximum likelihood (ML) based training and the synthesis application in HMM-based speech synthesis, a minimum generation error (MGE) criterion had been proposed for HMM training. This paper continues to apply the MGE criterion to model adaptation for HMM-based speech synthesis. We propose a MGE linear regression (MGELR) based model adaptation algorithm, where the regression matrices used to transform source models to target models are optimized to minimize the generation errors for the input speech data uttered by the target speaker. The proposed MGELR approach was compared with the maximum likelihood linear regression (MLLR) based model adaptation. Experimental results indicate that the generation errors were reduced after the MGELR-based model adaptation. And from the subjective listening test, the discrimination and the quality of the synthesized speech using MGELR were better than the results using MLLR.

[1]  Shun-ichi Amari,et al.  A Theory of Adaptive Pattern Classifiers , 1967, IEEE Trans. Electron. Comput..

[2]  K. Tokuda,et al.  Speech parameter generation from HMM using dynamic features , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[3]  Frank K. Soong,et al.  Full HMM Training for Minimizing Generation Error in Synthesis , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[4]  Satoshi Imai,et al.  Cepstral analysis synthesis on the mel frequency scale , 1983, ICASSP.

[5]  Keiichi Tokuda,et al.  Hidden Markov models based on multi-space probability distribution for pitch pattern modeling , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[6]  Wu Guo,et al.  Minimum generation error criterion for tree-based clustering of context dependent HMMs , 2006, INTERSPEECH.

[7]  Ren-Hua Wang,et al.  Minimum Generation Error Training for HMM-Based Speech Synthesis , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[8]  Keiichi Tokuda,et al.  Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis , 1999, EUROSPEECH.

[9]  Keiichi Tokuda,et al.  Speech synthesis using HMMs with dynamic features , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[10]  Keiichi Tokuda,et al.  Adaptation of pitch and spectrum for HMM-based speech synthesis using MLLR , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[11]  Keiichi Tokuda,et al.  A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis , 2007, IEICE Trans. Inf. Syst..