Optimum MVF Estimation-Based Two-Band Excitation for HMM-Based Speech Synthesis

ETRI Journal

关键词: TTS;    speech synthesis;    HMM-based speech synthesis;    HTS;   

Others  :  1185799
DOI  :  10.4218/etrij.09.0209.0112

【 摘 要 】

The optimum maximum voiced frequency (MVF) estimation-based two-band excitation for hidden Markov model-based speech synthesis is presented. An analysis-by-synthesis scheme is adopted for the MVF estimation which leads to the minimum spectral distortion of synthesized speech. Experimental results show that the proposed method significantly improves synthetic speech quality.

   

【 参考文献 】

• [1]T. Yoshimura et al., "Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis," Proc. EUROSPEECH, vol. 5, 1999, pp. 2347-2350.
• [2]T. Fukada et al., "An Adaptive Algorithm for Mel-Cepstral Analysis of Speech," Proc. ICASSP, vol. 1, 1992, pp. 137-140.
• [3]T. Yoshimura et al., "Mixed Excitation for HMM-Based Speech Synthesis," Proc. EUROSPEECH, vol. 3, 2001, pp. 2263-2266.
• [4]S. Kim, J. Kim, and M. Hahn, "HMM-Based Korean Speech Synthesis System for Hand-Held Devices," IEEE Trans. Consum. Electron., vol. 52, no. 4, Nov. 2006, pp. 1384-1390.
• [5]X. Huang, A. Acero, and H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm, and System Development, Prentice Hall, New Jersey, 2001.