Modeling pitch trajectory by hierarchical HMM with minimum generation error training

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

Volumn , Issue , 2012, Pages 4017-4020

  Wu, Yi Jian ^a   Soong, Frank ^a  

^a MICROSOFT RESEARCH ASIA   (China)

Author keywords

hidden Markov model; hierarchical pitch model; minimum generation error; Speech synthesis

Indexed keywords

CLUSTERING PROCESS; CONTEXT DEPENDENT; HMM-BASED SPEECH SYNTHESIS; MODEL PARAMETERS; TEST DATA; TRAINING PROCESS; TREE-BASED MODEL;

CLUSTERING ALGORITHMS; HIDDEN MARKOV MODELS; SIGNAL PROCESSING; SPEECH SYNTHESIS;

TRAJECTORIES;

EID: 84867589421     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288799     Document Type: Conference Paper

References (14)

1. T. Masuko, K. Tokuda, T. Kobayashi, and S. Imai, "Speech synthesis from HMMs using dynamic features," in Proc. of ICASSP, pp. 389-392, 1996.
2. Z.-H. Ling, Y.-J. Wu, Y. Wang, L. Qin, and R.-H. Wang, "USTC system for Blizzard Challenge 2006 an improved HMM-based speech synthesis method", in Blizzard Challenge 2006.
3. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis," in Proc. of ICASSP, pp. 2347-2350, 1999.
4. K. Tokuda, T. Masuko, N. Miyazaki, and T. Kobayashi, "Hidden markov models based on multi-space probability distribution for pitch pattern modeling," in Proc. of ICASSP, pp. 229-232, 1999.
5. S. Sakai, "F0 modeling with multi-layer additive modeling based on a statistical learning technique," in Proc. of SSW5, pp. 151-154, 1999.
6. Y. Qian, H. Liang, and F. K. Soong, "Generating natural F0 trajectory with additive trees," in Proc. of Interspeech, pp. 2126-2129, 2008.
7. C.C. Wang, Z.H. Ling, B.F. Zhang, and L.R. Dai, "Multi-layer F0 modeling for HMM-based speech synthesis," in Proc. of ISCSLP, pp. 129-132, 2008.
8. H. Zen and N. Braunschweiler, "Context-dependent additive log F0 model for HMM-based speech synthesis," in Proc. of Interspeech, pp. 2126-2129, 2009.
9. M. Lei, Y.-J. Wu, F. K. Song, Z.-H. Ling, L.-R. Dai, "A Hierarchical F0 Modeling Method for HMM-based Speech Synthesis," in Proc. of Interspeech, pp. 2170-2173, 2010.
10. Y.-J. Wu and R.H. Wang, "Minimum generation error training for HMM-based speech synthesis," in Proc. of ICASSP, pp. 889-892, 2006.
11. Y.-J. Wu, R.H. Wang, and F. Soong "Full HMM training for minimizing generation error in synthesis," in Proc. of ICASSP, pp. 517-520, 2007.
12. Y.-J. Wu, W. Guo and R.H. Wang, "Minimum generation error criterion for tree-based clustering of context dependent HMMs," in Proc. of Interspeech, pp. 2046-2049, 2006.
13. Y.-J. Wu, L. Qin, and K. Tokuda, "An improved minimum generation error based model adaptation for HMM-based speech synthesis," in Proc. of Interspeech, pp. 1787-1790, 2009.
14. K. Shinoda and T.Watanabe "MDL-based context dependent subword modeling for speech recognition," in J. Acoust. Soc. Jpn.(E), vol. 21, no. 2, pp. 79-86, 2000.