Combining Gaussian mixture model with global variance term to improve the quality of an HMM-based polyglot speech synthesizer

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 4, Issue , 2007, Pages

  Latorre, Javier ^a,b   Iwano, Koji ^a   Furui, Sadaoki ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^b TOSHIBA CORPORATION   (Japan)

Author keywords

Gaussian mixture; Global variance; HMM based speech synthesis; Polyglot

Indexed keywords

GAUSSIAN MIXTURE; GLOBAL VARIANCE; HMM-BASED SPEECH SYNTHESIS; POLYGLOTS;

ALGORITHMS; HIDDEN MARKOV MODELS; MATHEMATICAL MODELS; OPTIMIZATION;

SPEECH SYNTHESIS;

EID: 34547497133     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2007.367301     Document Type: Conference Paper

References (7)

1. Iwano, K., Yamada, M., Togawa, T. and Furui. S., Prosody Control for HMM-based Japanese TTS, Text to Speech Synthesis. New Paradigms and Advances, Shrikanth Narayanan and Abeer Alwan (Eds.), Prentice Hall PTR, pp. 155-173, July 2004.
2. Latorre, J., Iwano, K. and Sadaoki, F., New approach to the polyglot speech generation by means of an HMM-based speaker adaptable synthesizer, Speech Communication, Vol. 48, Issue 10, pp. 1227-1242, October 2006.
3. Schultz, T., Globalphone: a multilingual speech and text database developed at Karlsruhe University. Proc. ICSLP, pp. 345-348, September 2002.
4. Tachiwa, W. and Furui, S., A study of speech synthesis using HMMs. Proc. of Spring Meeting of the Acoustical Society of Japan (ASJ), Vol. 1, pp.239-240, March 1999. (In Japanese)
5. Toda, T. and Tokuda, K., Speech parameter generation algorithm considering global variance for HMM-based speech synthesis. Proc. Interspeech. pp. 2801-2804, September 2005.
6. Tokuda, K., Yoshimura, T., Masuko, T., Kobayashi, T., and Kitamura, T., Speech parameter generation algorithm for HMM-based speech synthesis. Proc. ICASSP, pp. 1315-1318, June 2000.
7. Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T. and Kitamura, T., Mixed excitation for HMM-based speech synthesis. Proc. Eurospeech, pp 2263-2266, September 2003.