Feature transform in linear spectral domain for fast channel adaptation

Electronics Letters

Volumn 40, Issue 20, 2004, Pages 1313-1315

  Kim, D ^a   Yook, D ^a  

^a Korea University   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

COMMUNICATION CHANNELS (INFORMATION THEORY); FEATURE EXTRACTION; FUNCTIONS; MATHEMATICAL TRANSFORMATIONS; MATRIX ALGEBRA; MAXIMUM LIKELIHOOD ESTIMATION; RANDOM PROCESSES; REGRESSION ANALYSIS;

FEATURE TRANSFORM ALGORITHMS; MAXIMUM LIKELIHOOD LINEAR REGRESSION (MILLR); MAXIMUM LIKELIHOOD SPECTRAL TRANSFORM (MLST); NONLINEAR ADAPTATION;

COMMUNICATION SYSTEMS;

EID: 6444225123     PISSN: 00135194     EISSN: None     Source Type: Journal    
DOI: 10.1049/el:20045484     Document Type: Article

References (4)

1. Kim, D., and Yook, D.: 'Fast channel adaptation for continuous density HMMs using maximum likelihood spectral transform', Electron. Lett., May 13, 2004, 40, (10), pp. 632-633
2. Leggetter, C.J., and Woodland, P.C.: 'Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models', Computer Speech Long., 1995, 9, pp. 171-185
3. Sankar, A., and Lee, C.H.: 'A maximum likelihood approach to stochastic matching for robust speech recognition', IEEE Trans. Speech Audio Process., May 1996, 4, pp. 190-202
4. Baum, L.: 'An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process', Inequalities, 1972, 3, pp. 1-8