Use of generalized spectral subtraction and missing feature compensation for robust speaker verification

RLA2C 1998 - Speaker Recognition and its Commercial and Forensic Applications

Volumn , Issue , 2020, Pages 80-83

  Drygajlo, Andrzej ^a   El Maliki, Mounir ^a  

^a EPFL   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

DIGITAL FORENSICS; GAUSSIAN DISTRIBUTION; SPEECH ANALYSIS; SPEECH ENHANCEMENT;

GAUSSIAN MIXTURE MODEL; GENERALIZED SPECTRAL SUBTRACTION; NOISE COMPENSATION; PROBABILITY COMPUTATIONS; ROBUST SPEAKER VERIFICATION; SPEAKER RECOGNITION; SPEAKER VERIFICATION SYSTEM; SPECTRAL SUBTRACTIONS;

SPEECH RECOGNITION;

EID: 85081108306     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. ACERO, A. Acoustical and Environmental Robustness in Automatic Speech Recognition. Kluwer Academic Publishers, 1993.
2. BEROUTI, M., SCHWARTZ, R., AND MAKHOUL, J. Enhancement of speech corrupted by acoustic noise. In Proc. ICASSP'79 (April 1979), pp. 208-211.
3. BOLL, S. Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. on Acoustics, Speech, and Signal Processing 27, 2 (April 1979), 113-120.
4. COOKE, M., GREEN, P., ANDERSON, C, AND AB-BERLEY, D. Recognition of occluded speech by hidden Markov models. Tech. rep., University of Sheffield, Department of Computer Science, 1994. TR-94-05-01.
5. COOKE, M., MORRIS, A., AND GREEN, P. Missing data techniques for robust speech recognition. In Proc. ICASSP (Munich, April 1997), pp. 863-866.
6. DEMSPTER, A., LAIRD, N., AND RUBIN, D. Maximum likelihood from incomplete data via the EM algorithm. J. Royal Statistical Soc. 39 (1977), 1-38.
7. LIM, J., AND OPPENHEIM, A. Enhancement and bandwidth compression of noisy speech. Proc. of the IEEE 67, 12 (1979), 1586-1604.
8. LIPPMAN, R. P., AND CARLSON, B. A. Using missing feature theory to actively select features for robust speech recognition with interruptions, filtering, and noise. In Proc. EUROSPEECH'97 (Rhodes, Sep. 1997), vol. 1, pp. KN 37-40.
9. LOCKWOOD, P., AND BOUDY, J. Experiments with a nonlinear spectral subtraction (NSS) and hidden Markov models and projection for robust recognition in cars. Speech Communications 11, 2-3 (June 1992), 215-228.
10. ORTEGA-GARCÍA, J., AND GONZÀLEZ-RODRÍGUEZ, J. Overview of speech enhancement techniques for automatic speaker recognition. In Proc. ICSLP (Oct. 1996), vol. 2, pp. 929-932.
11. REYNOLDS, D. Speaker identification and verification using Gaussian mixture speaker models. Speech Communication 17 (1995), 91-108.
12. REYNOLDS, D., AND ROSE, R. Robust text-independent speaker identification using Gaussian mixture models. IEEE Trans. on Speech Audio Processing 3 (1995), 72-83.