Minimum unit selection error training for HMM-based unit selection speech synthesis system

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

Volumn , Issue , 2008, Pages 3949-3952

  Ling, Zhen Hua ^a   Wang, Ren Hua ^a  

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

Author keywords

Discriminative training; HMM; Minimum unit selection error; Speech synthesis; Unit selection

Indexed keywords

ACOUSTICS; COMPUTER NETWORKS; DATABASE SYSTEMS; HIDDEN MARKOV MODELS; PARAMETER ESTIMATION; PROBABILITY DISTRIBUTIONS; SIGNAL PROCESSING; SPEECH RECOGNITION; SPEECH SYNTHESIS; TELEPHONE SETS;

DISCRIMINATIVE TRAINING; HMM; MINIMUM UNIT SELECTION ERROR; UNIT SELECTION;

TELEPHONE SYSTEMS;

EID: 51449107004     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2008.4518518     Document Type: Conference Paper

References (8)

1. Hunt, A.J.,and Black, A.W., "Unit selection in a concatenative speech synthesis system using large database", Proc. of ICASSP, 1996, pp.373-376.
2. Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., and Kitamura, T., "Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis," Proc. of Eurospeech, 1999, vol. 5, pp. 2347-2350.
3. Zhenhua Ling, and Renhua Wang, "HMM-based Hierarchical Unit Selection Combining Kullback-Leibler Divergence with Likelihood Criterion", Proc. of ICASSP, 2007, pp. 1245-1248.
4. Zhenhua Ling, Long Qin, Heng Lu, Yu Gao, Lirong Dai, Renhua Wang, Yuan Jiang, Zhiwei Zhao, Jinhui Yang, Jie Chen, and Guoping Hu" "The USTC and iflytek speech synthesis systems for Blizzard Challenge 2007", Blizzard Challenge Workshop, 2007.
5. Juang B, Chou W, and Lee C., "Minimum classification error rate methods for speech recognition", IEEE Transactions on Speech and Audio Processing, 1997, vol. 5, pp.257-265.
6. Kawahara, H., Masuda-Katsuse, I., and Cheveigne, A., "Restructuring speech representations using pitch-adaptive timefrequency smoothing and an instantaneous-frequency-based F0 extraction: possible role of a repetitive structure in sounds," Speech Communication, 1999, vol. 27, pp. 187-207.
7. Tokuda, K., Masuko, T., Miyazaki, N., and Kobayashi, T., "Hidden Markov models based on multi-space probability distribution for pitch pattern modeling", Proc. of ICASSP, 1999, pp. 229-232.
8. Blum, R.J., "Multidimensional stochastic approximation method", Ann. Mat. Stat., 1954, vol. 25, pp. 737-744.