Noise robust speaker identification using sub-band weighting in multi-band approach

IEICE Transactions on Information and Systems

Volumn E90-D, Issue 12, 2007, Pages 2110-2114

  Kim, Sungtak ^a   Ji, Mikyong ^a   Suh, Youngjoo ^a   Kim, Hoirin ^a  

^a Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

Feature recombination; Multi band approach; Speaker identification; Sub band likelihood; Sub band weighting

Indexed keywords

LOUDSPEAKERS; SIGNAL TO NOISE RATIO;

FEATURE RECOMBINATION; LIKELIHOOD COMPUTATION; MULTI BAND; PERFORMANCE IMPROVEMENTS; RECOMBINATION METHODS; SPEAKER IDENTIFICATION; SPEAKER IDENTIFICATION SYSTEMS; SUBBANDS;

SPEECH RECOGNITION;

EID: 68249155208     PISSN: 09168532     EISSN: 17451361     Source Type: Journal    
DOI: 10.1093/ietisy/e90-d.12.2110     Document Type: Article

References (6)

1. D. Reynold and R.C. Rose, "Robust text independent speaker identification using Gaussian mixture speaker models," Proc. IEEE Trans. Speech and Audio Processing, vol. 3, pp. 72-83, Jan. 1995.
2. S. Okawa, E. Bocchieri, and A. Potamianos, "Multi-band speech recognition in noise environments," Proc. ICASSP, pp. 641-644, 1998.
3. B. Mak, "A mathematical relationship between full-band and multiband mel-frequency cepstral coefficients," IEEE Signal Process. Lett., vol. 9, no. 8, pp. 241-244, 2002.
4. M. Berouti, R. Schwartz, and J. Makhoul, "Enhancement of speech corrupted by acoustic noise," Proc. ICASSP, pp. 208-211, 1979.
5. D. Pearce and H. Hirsch, "The aurora experimental framework for the performance evaluation of speech recognition systems under noise conditions," Proc. ICSLP, vol. 4, pp. 29-32, 2000.
6. D. Reynolds, T. Quatieri, and R. Dunn, "Speaker verification using adapted Gaussian mixture models," Digit. Signal Process., vol. 10, pp. 19-41, 2000.