Trajectory training considering global variance for HMM-based speech synthesis

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

Volumn , Issue , 2009, Pages 4025-4028

  Toda, Tomoki ^a   Young, Steve ^b  

^a NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

^b UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

Global varian; Hidden Markov models; Speech synthesis; Training criterion; Trajectory likelihood

Indexed keywords

CLOSED FORM SOLUTIONS; GLOBAL VARIAN; HMM-BASED SPEECH SYNTHESIS; NATURAL SPEECH; NOVEL METHODS; OPTIMIZATION CRITERIA; PARAMETER OPTIMIZATION; STATISTICAL MODELING; SYNTHESIS OPTIMIZATION; SYNTHETIC SPEECH; TRAINING CRITERION; TRAINING METHODS; UNIFIED FRAMEWORK;

ACOUSTICS; COMPUTATIONAL GRAMMARS; SIGNAL PROCESSING; SPEECH SYNTHESIS; STRUCTURAL OPTIMIZATION; TRAJECTORIES;

HIDDEN MARKOV MODELS;

EID: 67650826181     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2009.4960511     Document Type: Conference Paper

References (12)

1. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura. Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis. Proc. EUROSPEECH, pp. 2347-2350, Budapest, Hungary, Sep. 1999.
2. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura. Speech parameter generation algorithms for HMM-based speech synthesis. Proc. ICASSP, pp. 1315-1318, Istanbul, Turkey, June 2000.
3. H. Zen, K. Tokuda, and T. Kitamura. Reformulating the HMM as a trajetory model by imposing explicit relationships between static and dynamic feature vector sequences. Computer Speech and Language, Vol. 21, pp. 153-173, 2007.
4. Y.-J. Wu and R.H. Wang. Minimum generation error training for HMM-based speech synthesis. Proc. ICASSP, pp. 89-92, Toulouse, France, May 2006.
5. T. Toda and K. Tokuda. A speech parameter generation algorithm considering global variance for HMM-based speech synthesis. IEICE Transactions, Vol. E90-D, No. 5, pp. 816-824, May 2007.
6. Y.-J.Wu, H. Zen, Y. Nankaku and K. Tokuda. Minimum generation error criterion considering global/local variance for HMM-based speech synthesis. Proc. ICASSP, pp. 4621-4624, Las Vegas, USA, Mar. 2008.
7. K. Nakamura. Model training considering global variance for HMMbased speech synthesis. Master Thesis (in Japanese), Nagoya Institute of Technology, 2007.
8. K. Tokuda, T. Masuko, N. Miyazaki, and T. Kobayashi. Multi-space probability distribution HMM. IEICE Trans. Inf. and Syst., Vol. E85-D, No. 3, pp. 455-464, 2002.
9. K. Tokuda, T. Kobayashi, T. Masuko, and S. Imai. Mel-generalized cepstral analysis - a unified approach to speech spectral estimation. Proc. ICSLP, pp. 1043-1045, Yokohama, Japan, Sep. 1994.
10. J. Kominek and A. W. Black. CMU ARCTIC databases for speech synthesis. Technical Report, CMU-LTI-03-177, Language Technologies Institute, Carnegie Mellon University, 2003.
11. http://www.speech.cs.cmu.edu/flite/index.html
12. 0 extraction: possible role of a repetitive structure in sounds. Speech Communication, Vol. 27, No. 3-4, pp. 187-207, 1999.