Minimum generation error training with direct log spectral distortion on LSPs for HMM-based speech synthesis

A minimum generation error (MGE) criterion had been proposed to solve the issues related to maximum likelihood (ML) based HMM training in HMM-based speech synthesis. In this paper, we improve the MGE criterion by imposing a log spectral distortion (LSD) instead of the Euclidean distance to define the generation error between the original and generated line spectral pair (LSP) coefficients. Moreover, we investigate the effect of different sampling strategies to calculate the integration of the LSD function. From the experimental results, using the LSDs calculated by sampling at LSPs achieved the best performance, and the quality of synthesized speech after the MGE-LSD training was improved over the original MGE training.

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

[2]  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).

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

[4]  F. Itakura.  Line spectrum representation of linear predictor coefficients of speech signals , 1975 .

[5]  Hideki Kawahara,et al.  Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds , 1999, Speech Commun..

[6]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[7]  Ren-Hua Wang,et al.  USTC System for Blizzard Challenge 2006 an Improved HMM-based Speech Synthesis Method , 2006 .

[8]  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.

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

[10]  Heiga Zen,et al.  Speaker-Independent HMM-based Speech Synthesis System , 2007 .

[11]  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.

[12]  Heiga Zen,et al.  An overview of nitech HMM-based speech synthesis system for blizzard challenge 2005 , 2005, INTERSPEECH.