Improved modeling for F0 generation and V/U decision in HMM-based TTS

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

Volumn , Issue , 2010, Pages 4606-4609

  Zhang, Qingqing ^a,b   Soong, Frank ^a   Qian, Yao ^a   Yan, Zhijie ^a   Pan, Jielin ^b   Yan, Yonghong ^b  

^a MICROSOFT RESEARCH ASIA   (China)

^b INSTITUTE OF ACOUSTICS   (China)

Author keywords

F0 generation; HMM based TTS; V U decision model; Voicing strength

Indexed keywords

EXTRACTION; PROBABILITY DENSITY FUNCTION; SIGNAL PROCESSING;

DECISION MODELING; F0 GENERATION; F0 MODELING; HMM-BASED; HMM-BASED TTS; NEW APPROACHES; SYNTHESIZED SPEECH; TRAINING DATA; V/U DECISION MODEL; VOICING STRENGTH;

ERRORS;

EID: 78049409326     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495561     Document Type: Conference Paper

References (15)

1. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech Parameter Generation Algorithms for HMM-based Speech Synthesis", Proc. of ICASSP, 2000.
2. H. Kawahara, I. M. Katsuse, and A. D. Cheveigne, "Restructuring speech representations using a pitch-adaptive timefrequency smoothing and an instantaneous-frequency-based f0 extraction: possible role of a repetitive structure in sounds", Speech Communication, vol. 27, no. 3-4, pp. 187-207, 1999.
3. J. Yamagishi, Z. Ling, and S. King, "Robustness of HMM-based Speech Synthesis", Proc. of InterSpeech, 2008.
4. D. Arifianto, T. Tanaka, T. Masuko, and T. Kobayashi, "Robust F0 estimation of speech signal using harmonicity measure based on instantaneous frequency", IEICE Trans. Inf. & Syst., vol. E87-D, no. 12, pp. 2812-2820, Dec. 2004.
5. H. Kawahara, H. Katayose, A. Cheveigńe, and R. Patterson, "Fixed point analysis of frequency to instantaneous frequency mapping for accurate estimation of F0 and periodicity", Proc .of EuroSpeech, 1999.
6. D. Talkin, "A robust algorithm for pitch tracking (RAPT)", in Speech Coding and Synthesis,W. Kleijn and K. Paliwal, Eds. Elsevier, 1995, pp. 495-518.
7. 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," Computer Speech & Language, vol. 21, no. 1, pp. 153-173, 2007.
8. Y. Wu, R. Wang, and F. Soong, "Full HMM Training for Minimizing Generation Error in Synthesis," in Proc. ICASSP,2007.
9. K. Yu, T. Toda, M. Gasic, S. Keizer, F. Mairesse, B. Thomson and S. Young, "Probablistic modelling of f0 in unvoiced regions in hmm based speech synthesis," ICASSP 2009, Taipei, Taiwan, April 19-24.
10. T. Masuko, K. Tokuda, N. Miyazaki, and T. Kobayashi, "Pitch pattern generation using multi-space probability distribution hmm," IEICE Trans., vol. J83-D-II, no. 7, pp. 1600-1609, 2000
11. Y. Qian, F. k. Soong, M. Wang, Z. Wu, "A Minimum V/U Error Approach to F0 Genearation in HMM-based TTS", In Proc. InterSpeech 2009.
12. S. Kang, Z. Shuang, Q. Duan, Y. Qin, L. Cai, "Voiced/Unvoiced Decision Algorithm for HMM-based Speech Synthesis", in Proc. of Interspeech2009, Brighton, UK, Sept. 2009.
13. C.J. Chen, R.A. Gopinath, M.D. Monkowski,M.A. Picheny, K. Shen, "New methods in continuous Mandarin speech recognition", In Proc. of Eurospeech 1997, pp. 1543-1546.
14. K. Shinoda, and T. Watanable, "MDL-based Context-Dependent Sub-word Modeling for Speech Recognition", J. Acoust. Soc. Jpn(E), vol.21, no.2, pp.79-86, 2000.
15. "HMM-based Speech Synthesis System (HTS)," http://hts.sp. nitech.ac.jp. 2009