Factor analyzed voice models for HMM-based speech synthesis

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

Volumn , Issue , 2010, Pages 4234-4237

  Kazumi, Kyosuke ^a   Nankaku, Yoshihiko ^a   Tokuda, Keiichi ^a  

^a NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Deterministic annealing; Eigenvoice; EM algorithm; Expectation maximization algorithm; Factor analysis; HMM based speech synthesis

Indexed keywords

IMAGE SEGMENTATION; MAXIMUM PRINCIPLE; SPEECH RECOGNITION; SPEECH SYNTHESIS;

DETERMINISTIC ANNEALING; EIGENVOICES; EM ALGORITHMS; EXPECTATIONS MAXIMIZATION ALGORITHMS; FACTORS ANALYSIS; HMM-BASED SPEECH SYNTHESIS; SPEECH MODELS; TRAINING DATA; VOICE CHARACTERISTICS; VOICE MODEL;

DECISION TREES;

EID: 78049397015     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495689     Document Type: Conference Paper

References (6)

1. T. Masuko, K. Tokuda, T. Kobayashi, and S. Imai, "Speech synthesis from HMMs using dynamic features," Proc. of ICASSP, pp.389-392, 1996.
2. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch, and duration in HMM-based speech synthesis," Proc. of EUROSPEECH, pp.2347-2350, 1999.
3. K. Shichiri, A. Sawabe, T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Eigenvoices for HMM-based speech synthesis," Proc. of ICSLP, vol.1, pp.1269-1272, 2002.
4. M. I. Jordan, Z. Ghahramani, T. S. Jaakkola, and L. K. Saul, "An introduction to variational methods for Graphical models," Machine Learing, vol.37, pp.183-233, 1997.
5. N. Ueda and R. Nakano, "Determinisic annealing EM algorithm," Neural Networks, vol.11, no.2, pp.271-282, 1998
6. J. Yamagishi, M. Tamura, T. Masuko, K. Tokuda, and T. Kobayashi, "A context clustering technique for average voice model in HMM-based speech synthesis," Proc. of ICSLP, pp. 133-136, 2002.