Speaker adaptation using discriminative linear regression on time-varying mean parameters in trended HMM

IEEE Signal Processing Letters

Volumn 5, Issue 3, 1998, Pages 63-65

  Chengalvarayan, Rathinavelu ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

Hidden Markov model; Linear regression; Maximum likelihood; Minimum classification error; Speaker adaptation

Indexed keywords

ERROR ANALYSIS; LEARNING ALGORITHMS; MARKOV PROCESSES; MATHEMATICAL MODELS; PARAMETER ESTIMATION; POLYNOMIALS; REGRESSION ANALYSIS;

HIDDEN MARKOV MODELS (HMM); MAXIMUM LIKELIHOOD LINEAR REGRESSION (MLLR); MINIMUM CLASSIFICATION ERROR (MCE) TRAINING ALGORITHMS; MINIMUM CLASSIFICATION ERROR LINEAR REGRESSION (MCELR); SPEAKER ADAPTATION;

SPEECH RECOGNITION;

EID: 0032028378     PISSN: 10709908     EISSN: None     Source Type: Journal    
DOI: 10.1109/97.661562     Document Type: Article

References (8)

1. C. M. Ayer, M. J. Hunt, and D. M. Brookes, "A discriminatively derived linear transform for improved speech recognition," in Proc. EUROSPEECH, 1993, vol. 1, pp. 583-586.
2. L. Deng, M. Aksmanovic, X. Sun, and J. Wu, "Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states," IEEE Trans. Speech Audio Processing, vol. 2, pp. 507-520, 1994.
3. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol. 9, pp. 171-185, 1995.
4. T. Matsui and S. Furui, "A study of speaker adaptation based on minimum classification error training," in Proc. EUROSPEECH, 1995, vol. 1, pp. 81-84.
5. M. Padmanabhan, L. Bahl, D. Nahamoo, and M. Picheny, "Speaker clustering and transformation for speaker adaptation in large-vocabulary speech recognition systems," in Proc. ICASSP, 1996, vol. 2, pp. 701-704.
6. C. Rathinavelu and L. Deng, "The trended HMM with discriminative training for phonetic classification," in Proc. ICSLP, 1996, vol. 2, pp. 1049-1052.
7. A. Sankar, L. Neumeyer, and M. Weintraub, "An experimental study of acoustic adaptation algorithms," in Proc. ICASSP, 1996, vol. 2, pp. 713-716.
8. J. Takahashi and S. Sagayama, "Minimum classification error training for a small amount of data enhanced by vector-field-smoothed Bayesian learning," in Proc. ICASSP, 1996, vol. 2, pp. 597-600.