Phone duration modeling using gradient tree boosting

Speech Communication

Volumn 50, Issue 5, 2008, Pages 405-415

  Yamagishi, Junichi ^a,b   Kawai, Hisashi ^a,c   Kobayashi, Takao ^b  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b Tokyo Institute of Technology ^*  (Japan)

^c KDDI CORPORATION   (Japan)

Author keywords

Gradient tree boosing; Phone duration modeling; Text to speech synthesis

Indexed keywords

ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; REGRESSION ANALYSIS; SPEECH INTELLIGIBILITY;

GRADIENT TREE BOOSING; PHONE DURATION MODELING; TEXT-TO-SPEECH SYNTHESIS;

TREES (MATHEMATICS);

EID: 41049090228     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2007.12.003     Document Type: Article

References (18)

1. Breiman L. Bagging predictors. Machine Learn. 24 (1996) 123-140
2. Campbell W.N. Analog I/O nets for syllable timing. Speech Comm. 9 (1990) 57-61
3. Chen S.H., Lai W.H., and Wang Y.R. A new duration modeling approach for Mandarin speech. IEEE Trans. Speech. Audio Process. 11 4 (2003) 308-320
4. Friedman J.H. Greedy function approximation: a gradient boosting machine. Ann. Statist. 29 5 (2001) 1189-1232
5. Friedman J.H. Stochastic gradient boosting. Comput. Statist. Data Anal. 38 4 (2002) 367-378
6. Hastie T., Tibshirani R., and Friedman J.H. The elements of statistical learning: data mining, inference, and prediction. Springer Series in Statistics (2001), Springer
7. Iwahashi N., and Sagisaka Y. Statistical modeling of speech segment duration by constrained tree regression. IEICE Trans. Inform. Systems, E83-D 7 (2000) 1550-1559
8. Kawai, H., Toda, T., Ni, J., Tsuzaki, M., Tokuda, K., 2004. XIMERA: a new TTS from ATR based on corpus-based technologies. In: Proc. 5th ISCA Speech Synthesis Workshop, pp. 179-184.
9. Kawai, H., Toda, T., Yamagishi, J., Hirai, T., Ni, J., Nishizawa, N., Tsuzaki, M., Tokuda, T., 2006. XIMERA: a concatenative speech synthesis system with large scale corpora. IEICE Trans., pp. 2688-2698, J89-D-II, 12 (in Japanese).
10. Lee, S., Oh, Y., 1999. CART-based modelling of Korean segmental duration. In: Proc. Oriental COCOSDA'99, pp. 109-112.
11. Quinlan, J.R., 1992. Learning with continuous classes. In: Proc. AI'92, pp. 343-348.
12. Riedi, M., 1995. A neural-network-based model of segmental duration for speech synthesis. In: Proc. EUROSPEECH-95, pp. 599-602.
13. Riley M.D. Tree-based modelling of segmental duration. In: Bailly G., and Benoît C. (Eds). Talking Machines: Theories, Models and Designs (1992), Elsevier, Amsterdam 265-273
14. Snyman J.A. Practical Mathematical Optimization: An Introduction to Basic Optimization Theory and Classical and New Gradient-Based Algorithms (2005), Springer
15. Takeda K., Sagisaka Y., and Kuwabara H. On sentence-level factors governing segmental duration in Japanese. J. Acous. Soc. Am. 86 6 (1989) 2081-2087
16. Takezawa, T., Sumita, E., Sugaya, F., Yamamoto, H., Yamamoto, S., 2002. Toward a broad-coverage bilingual corpus for speech translation of travel conversations in the real world, In: Proc. of LREC 2002, pp. 147-152.
17. van Santen J., and Olive J. The analysis of contextual effects on segmental duration. Comput. Speech Langu. 4 (1990) 359-390
18. Witten I.H., and Frank E. Data Mining: Practical Machine Learning Tools and Techniques. Second ed. (2005), Morgan Kaufman