SPEAKER ADAPTATION BASED ON TRANSFER VECTOR FIELD SMOOTHING WITH CONTINUOUS MIXTURE DENSITY HMMs

2nd International Conference on Spoken Language Processing, ICSLP 1992

Volumn , Issue , 1992, Pages 369-372

  Ohkura, Kazumi ^a   Sugiyama, Masahide ^a   Sagayama, Shigeki ^a  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS MIXTURES; MIXTURE DENSITY; PHONEMES RECOGNITION; SMOOTHING METHODS; SPEAKER ADAPTATION; SPEAKING STYLES; TRAINING DATA; VECTOR FIELDS;

EID: 85135109228     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Y. Hirata and S. Nakagawa. "A Study of Speaker Adaptation of Continuous Parameter HMM on Japanese Phoneme Recognition," Tech. report of IEICE, SP90-16, (Jun. 1990).
2. Y. Nakato and H. Matsumoto. "A Study on Unsupervized Speaker Adaptation of Continuous Parameter HMM," Tech. report of IEICE, SP90-67, pp. 79-86 (Dec. 1990).
3. S. Mizuta and K. Nakajima. "An Optimal Discriminative Training Method for Speaker-Independent Word Recognition Using Continuous Mixture Density Acoustic-Phonetic Segment HMMs," Tech. report of IEICE, SP91-58, pp. 21-28 (Sep. 1991).
4. T. Matsuoka and K. Shikano. "Speaker Adaptation by Modifying Mixture Coefficients of Speaker Independent Mixture Gaussian HMMs," Proc. of Meeting of Acoust. Soc. of Japan, 1-1-6, pp. 11-12 (Mar. 1992).
5. T. Iwahashi and K. Nakajima. "Continuous Mixture Densities Based Speaker Adaptation for Acoustic Phonetic Segment HMM," Proc. of Meeting of Acoust. Soc. of Japan, 1-5-21, pp. 45-46 (Mar. 1991).
6. C. H. Lee, C. H. Lin and B. H. Juang. "A Study on Speaker Adaptation of the Parameters of Continuous Density Hidden Markov Models," IEEE Trans, on SP, Vol.39, pp. 806-814 (Apr. 1991).
7. F. Kubala, R. Schwartz and C. Barry. "Speaker Adaptation from a Speaker-Independent Training Courpus," Proc. of ICASSP90, pp. 137-140 (Apr. 1990).
8. K. Ohkura, M. Sugiyama and S. Sagayama. "Speaker Adaptation Based on Transfer Vector Field Smoothing Model with Continuous Mixture Density HMMs," Proc. of Meeting of Acoust. Soc. of Japan, 2-Q-17, pp. 191-192 (Mar. 1992).
9. T. Matsuoka and K. Shikano. "Robust HMM Phoneme Modeling for Different Speaking Styles," Proc. of ICASSP91, S5.4, pp. 265-268, (May 1991).
10. T. Hanazawa and K. Nakajima. "Study of Speaker Independent Continuous Speech Recognition Using Speaking-Style Dependent HMM," Proc. of Meeting of Acoust. Soc. of Japan, 2-1-1, pp. 51-52 (Mar. 1992).
11. K. Yamaguchi and S. Sagayama. "HMM-LR Continuous Speech Recognition Using Continuous Mixture HMMs," Proc. of Meeting of Acoust. Soc. of Japan, l-P-5, pp. 113-114 (Mar. 1992).
12. Y. Kato and M. Sugiyama. "Continuous Speech Recognition Using Neural Networks with Multiple Input-Output Units," Proc. of Meeting of Acoust. Soc. of Japan, 3-1-1, pp. 71-72 (Mar. 1992).
13. H. Hattori and S. Sagayama. "Speaker Adaptation with Small Size Data Based on Codebook Mapping Algorithm," Proc. of Meeting of Acoust. Soc. of Japan, 1-5-23, pp. 49-50 (Mar. 1991).
14. Y. Shiraki and M. Honda. "Speaker Adaptation Algorithm for Segment Vocoder," Tech. report of IEICE, SP87-67, pp. 49-56 (Oct. 1987).
15. T. Hanazawa, T. Kawabata and K. Shikano. "Recognition of Japanese Voiced Stops Using Hidden Markov Models," J. Acoust. Soc. Japan., Vol. 45, No. 10, pp. 776-783 (Oct. 1989).
16. T. Kawabata, T. Hanazawa and K. Shikano. "Word Spotting Method Based on HMM Phoneme Recognition," Proc. of Meeting of Acoust. Soc. of Japan, 3-P-5, pp. 237-238 (Mar. 1988).
17. S. Nakamura, T. Hanazawa and K. Shikano. "Phoneme Recognition Evaluation of HMM Speaker Adaptation Based on Vector Quantization," Tech. report of IEICE, SP88-106, pp. 1-8 (Dec. 1988).
18. K. Shinoda, K. Iso, and T. Watanabe. "Speaker Adaptation For Demi-Syllable Based Continuous Density HMM," Proc. of ICASSP91, S13.7, pp. 857-860 (May. 1991).