A hierarchical F0 modeling method for HMM-based speech synthesis

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Volumn , Issue , 2010, Pages 2170-2173

  Lei, Ming ^a,b   Wu, Yi Jian ^b   Soong, Frank K ^c   Ling, Zhen Hua ^a   Dai, Li Rong ^a  

^a UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA   (China)

^b MICROSOFT   (United States)

^c MICROSOFT RESEARCH ASIA   (China)

Author keywords

Hidden Markov model; Hierarchical F0 modeling; Minimum generation error; Speech synthesis

Indexed keywords

HIDDEN MARKOV MODELS; SPEECH COMMUNICATION; SPEECH SYNTHESIS; CONTINUOUS SPEECH RECOGNITION;

DIFFERENT LAYERS; F0 MODEL; HMM-BASED SPEECH SYNTHESIS; MINIMUM GENERATION ERRORS; MODEL TRAINING; PROSODIC FEATURES; TRAINING DATA; TRAINING FRAMEWORK; F0 MODELING; HIDDEN-MARKOV MODELS; HIERARCHICAL F0 MODELING; MODEL METHOD; PROSODICS; SPEECH SYNTHESIS SYSTEM; STATE BASED;

CONTINUOUS SPEECH RECOGNITION; SPEECH SYNTHESIS;

EID: 79959844205     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. K. Tokuda, H. Zen, and A. W. Black, "HMM-based approach to multilingual speech synthesis," in Text to speech synthesis: New paradigms and advances, S. Narayanan and A. Alwan, Eds. Prentice Hall, 2004.
2. T. Yoshimura, K. Tokuda, T. Masuko, T. Kobayashi, and T. Kitamura, "Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis," in Sixth European Conference on Speech Communication and Technology. ISCA, 1999.
3. K. Tokuda, T. Kobayashi, and S. Imai, "Speech parameter generation from HMM using dynamic features," in Proc. of ICASSP, vol. 1, 1995, pp. 660-663.
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, vol. 1, 1999, pp. 229-232.
5. 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 ISC-SLP, 2008, pp. 129-132.
6. S. Sakai, "F0 modeling with multi-layer additive modeling based on a statistical learning technique," in Proc. ISCA SSW5. ISCA, 2004, pp. 151-154.
7. Y. Qian, H. Liang, and F. K. Soong, "Generating natural F0 trajectory with additive trees," in Proc. of Interspeech, 2008, pp. 2126-2129.
8. H. Zen and N. Braunschweiler, "Context-dependent additive log F0 model for HMM-based speech synthesis," in Proc. of Interspeech, 2009, pp. 2091-2094.
9. H. Fujisaki, "In search of models in speech communication reserach," in Proc. of Interspeech, 2008, pp. 1-10.
10. Y. J. Wu and R. H. Wang, "Minimum generation error training for HMM-based speech synthesis," in Proc. of ICASSP, vol. 1, 2006, p. I.
11. 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, 2009, pp. 1787-1790.
12. K. Shinoda and T. Watanabe, "MDL-based context dependent subword modeling for speech recognition," J. Acoust. Soc. Jpn. (E), vol. 21, no. 2, pp. 79-86, 2000. (Pubitemid 30594111)
13. M. Lei, Z. H. Ling, and L. R. Dai, "Minimum generation error training with weighted Euclidean distance on LSP for HMM-based speech synthesis," in Proc. of ICASSP, 2010, pp. 4230-4233.