Improved Prosody Generation by Maximizing Joint Probability of State and Longer Units

IEEE Transactions on Audio, Speech and Language Processing

Volumn 19, Issue 6, 2011, Pages 1702-1710

  Wu, Zhizheng ^a   Qian, Yao ^b   Soong, Frank K ^b   Gao, Boyang ^c  

^a NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

^b MICROSOFT RESEARCH ASIA   (China)

^c ECOLE CENTRALE DE LYON   (France)

Author keywords

Discrete cosine transforms (DCTs); speech synthesis; statistical distributions

Indexed keywords

EID: 85008039410     PISSN: 15587916     EISSN: 15587924     Source Type: Journal    
DOI: 10.1109/TASL.2010.2097248     Document Type: Article

References (31)

1. 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. Eurospeech, 1999, pp. 2347–2350.
2. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, “Speech parameter generation algorithms for HMM-based speech synthesis,” in Proc. ICASSP, 2000, pp. 1315–1318.
3. Y. Sagisaka, N. Kaiki, N. Iwahashi, and K. Mimura, “ATR μ -talk speech synthesis system,” in Proc. ICSLP, 1992, pp. 483–486.
4. A. Hunt and A. Black, “Unit selection in a concatenative speech synthesis system using a large speech database,” in Proc. ICASSP, 1996, pp. 373–376.
5. J. Yamagishi and T. Kobayashi “Average-voice-based speech synthesis using HSMM-based speaker adaptation and adaptive training,” IEICE Trans. Inf. Syst., vol. E90-D, no. 2, pp. 533–543, 2007.
6. T. Nose, J. Yamagishi, and T. Kobayashi “A style control technique for HMM-based expressive speech synthesis,” IEICE Trans. Inf. Syst., vol. E90-D, no. 9, pp. 1406–1413, 2007.
7. H. Zen, K. Tokuda, and A. W. Black “Statistical parametric speech synthesis,” Speech Commun., vol. 51, no. 11, pp. 1039–1064, 2009.
8. T. Toda and K. Tokuda, “Speech parameter generation algorithm considering global variance for HMM-Based speech synthesis,” in Proc. Eurospeech, 2005, pp. 373–376.
9. J. Latorre, K. Iwano, and S. Furui, “Combining gaussian mixture model with global variance term to improve the quality of an HMM-based polyglot speech synthesizer,” in Proc. ICASSP, 2007, pp. 1241–1244.
10. H. Zen, K. Tokuda, and T. Kitamura “Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences,” Comput. Speech Lang., vol. 21, no. 1, pp. 153–173, 2007.
11. Y.-J. Wu, R.-H. Wang, and F. K. Soong, “Full HMM Training for Minimizing Generation Error in Synthesis,” in Proc. ICASSP, 2007, pp. 517–520.
12. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, Data Mining, Inference, and Prediction. New York: Springer, 2001.
13. X.-J. Sun, “F0 generation for speech synthesis using a multi-tier approach,” in Proc. ICSLP, 2002, pp. 2077–2080.
14. S. Sakai, “Additive modeling of english f0 contour for speech synthesis,” in Proc. ICASSP, 2005, pp. 277–280.
15. Y.-J. Wu and R.-H. Wang “HMM-based trainable speech synthesis for Chinese,” J. Chinese Inf. Process., vol. 20, no. 4, pp. 75–81, 2006.
16. Y. Qian, H. Fiang, and F. K. Song, “Generating natural F0 trajectory with additive trees,” in Proc. Interspeech, 2008, pp. 2126–2129.
17. J. Yamagishi, H. Kawai, and T. Kobayashi “Phone duration modeling using gradient tree boosting,” Speech Commun., vol. 50, no. 5, pp. 405–415, 2008.
18. Y. Qian, Z.-Z. Wu, and F. K. Song, “Improved prosody generation by maximizing joint likelihood of state and longer units,” in Proc. ICASSP, 2009, pp. 3781–3784.
19. J. Latorre and M. Akamine, “Multilevel parametric-base F0 model for speech synthesis,” in Proc. Interspeech, 2008, pp. 2274–2277.
20. Y. Ishimatsu, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, “Investigation of state duration model based on gamma distribution for HMM-based speech synthesis,” IEICE Tech. Rep., vol. 101, no. 352, pp. 57–62, 2001.
21. S. J. Park, M. W. Koo, and C. S. Jhon “Context-Dependent phoneme duration modeling with Tree-Based state tying,” IEICE Trans. Inf. Syst., vol. E88-D, no. 3, pp. 662–666, 2005.
22. B.-Y. Gao, Y. Qian, Z.-Z. Wu, and F. K. Soong, “Duration refinement by jointly optimizing state and longer unit likelihood,” in Proc. Interspeech, 2008, pp. 2266–2269.
23. J. Teutenberg, C. Watson, and P. Riddle, “Modelling and synthesising F0 contours with the discrete cosine transform,” in Proc. ICASSP, 2008, pp. 3973–3976.
24. Z.-Z. Wu, Y. Qian, F. K. Soong, and B. Zhang, “Modeling and generating tone contour with phrase intonation for Mandarin Chinese speech,” in Proc. ISCSLP, 2008, pp. 121–124.
25. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, “Duration modeling for HMM-based speech synthesis,” in Proc. ICSLP, 1998, pp. 29–32.
26. K. Tokuda, T. Masuko, N. Miyazaki, and T. Kobayashi “Multi-space probability distribution HMM,” IEICE Trans. Inf. Syst., vol. E85-D(3), pp. 455–464, 2002.
27. G. W. Snedecor, Statistical Methods. Ames: Iowa State Univ. Press, 1989.
28. H. Kawahara, I. Masuda Katsuse, and A. de Cheveigne “Restructuring speech representations using pitch-adaptive time-frequency smoothing and instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds,” Speech Commun., vol. 27, no. 3–4, pp. 187–207, 1999.
29. A. D. Talkin, “chapter A robust algorithm for pitch tracking (RAPT),” in Speech Coding and Synthesis. Amsterdam, The Netherlands: Elservier, 1995.
30. K. Shinoda and T. Watanable “MDL-based context-dependent subword modeling for speech recognition,” J. Acoust. Soc. Jpn(E), vol. 21, no. 2, pp. 79–86, 2000.
31. Z.-H. Ling, Y.-J. Wu, Y.-P. Wang, L. Qin, and R.-H. Wang, “USTC system for blizzard challenge 2006 an improved HMM-based speech synthesis method,” in Proc. Blizzard Challenge 2006 Workshop, 2006.