Tree-structured speaker clustering for fast speaker adaptation

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

Volumn 1, Issue , 1994, Pages I245-I248

  Kosaka, Tetsuo ^a   Sagayama, Shigeki ^b  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b NTT CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

SIGNAL PROCESSING; TREES (MATHEMATICS);

ADAPTATION METHODS; CLUSTERING TREES; FAST SPEAKER ADAPTATION; PARAMETER TRAINING; RECOGNITION METHODS; SPEAKER ADAPTATION; SPEAKER CLUSTERING; SPEAKER INDEPENDENTS;

CLUSTERING ALGORITHMS;

EID: 85009078667     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1994.389309     Document Type: Conference Paper

References (10)

1. M. Sugiyama: "Unsupervised Speaker Adaptation Methods for Vowel Templates," Proc. of ICASSP86, pp. 2639-2642 (1986).
2. P. Niyogi and V. W. Zue: "Correlation Analysis of Vowels and Their Application to Speech Recognition," Proc. of Eurospeech 91, pp. 1253-1256 (1991).
3. S. Furui: "Unsupervised speaker adaptation method based on hierachical spectral clustering," Proc. of ICASSP89, Table 1. Experimental Conditions
4. T. Kosaka, J. Takami and S. Sagayama: "Rapid Speaker Adaptation Using Speaker-Mixture Allophone Models Applied to Speaker-Independent Speech Recognition," Proc. of ICASSP93, pp. 570-573, (1993).
5. J. Takami and S. Sagayama: "A Successive State Splitting Algorithm for Efficient Allophone Modeling," Proc. of ICASSP92, (1992).
6. B.-H. Juang and L. R. Rabinaer: "A Probabilistic Distance Measure for Hidden Markov Models," AT&T Technical Journal Vol. 64, No. 2, (1985.02).
7. V. Abrash, H. Franco, M. Cohen, N. Morgan and Y. Konig: "Connectionist Gender Adaptation in a Hybrid Neural Network / Hidden Markov Model Speech Recognition System," Proc. of ICSLP92, pp. 911-914 (1992).
8. N. Sugamura, K. Shikano and S. Furui: "Isolated word recognition losing phoneme-like templates," Proc. of ICASSP83, (1983).
9. K. Ohkura, M. Sugiyama and S. Sagayama: "Speaker Adaptation Based on Transfer Vector Field Smoothing with Continuous Mixture Density HMMs," Proc. of ICSLP92, We.fPM.1.1, pp. 369-372 (1992).
10. A. Nagai, et al.: "Phoneme-context-dependent LR Parsing Algorithms for HMM-based Continuous Speech Recognition," Proc. of Eurospeech'91, S48.3. (1991).