Abstract
In order to handle speech signals corrupted by noise in speaker verification and provide robustness to systems, this paper evaluates the use of missing feature (MF) approach with a novel combination of techniques. A mask estimation based on spectral subtraction is used to determine the reliability of spectral components in a speech signal corrupted by noise. A cluster based reconstruction technique is used to remake the damaged spectrum. The verification performance was evaluated through a speaker verification experiment with signals corrupted by white noise under different signal to noise ratios. The results were promising since they reflected a relevant increase of speaker verification performance, applying MF approach with this combination of techniques.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Benesty, J., Chen, J., Huang, Y., Cohen, I.: Noise Reduction in Speech Processing. Springer Topics in Signal Processing 2 (2009)
Raj, B., Stern, R.: Missing-Feature Approaches in Speech Recognition. In: IEEE Signal Proc. Magazine (2005)
Padilla, M., Quatieri, T., Reynolds, D.: MF Theory with Soft Spectral Subtraction for Speaker Verification (2006)
Ming, J., Hazen, T., Glass, J.R., Reynolds, D.A.: Robust Speaker Recognition in Noisy Conditions. IEEE Trans. on Speech and Audio Proc. 15, 1711–1723 (2007)
Pullella, D., Kuhne, M., Togneri, R.: Robust Speaker Identification Using Combined Feature Selection and Missing Data Recognition. In: ICASSP (2008)
Kuhne, M., Pullella, D., Togneri, R., Nordholm, S.: Towards the use of full covariance models for missing data speaker recognition. In: ICASSP (2008)
Cerisara, C., Demange, S., Haton, J.-P.: On noise masking for automatic missing data speech recognition: a survey and discussion. Computer Speech and Language 21(3), 443–457 (2007)
Drygajlo, A., El-Maliki, M.: Speaker Verification in Noisy Enviroments with Combined Spectral Subtraction and MF Theory. In: Signal Proc. Laboratory, Swiss Federal Institute of Technology at Lausanne (1998)
Pelecanos, J., Sridharan, S.: Feature warping for robust speaker verification. Speaker Odyssey (2001)
Raj, B., Seltzer, M., Stern, R.M.: Reconstruction of MFs for robust speech recognition. Speech Communication 43 (2004)
Seltzer, M., Raj, B., Stern, R.M.: A Bayesian classifier for spectrographic mask estimation for MF speech recognition. Speech Communication 43 (2004)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society (1977)
The NIST year, speaker recognition evaluation plan (2006), http://www.nist.gov/speech/tests/spk/2006/index.htm
Berouti, M., Schwartz, R., Makhoul, J.: Enhancement of speech corrupted by acoustic noise. In: IEEE ICASSP (1979)
Martin, R.: Noise Power Spectral Density Estimation Based on Optimal Smoothing and Minimum Statistics. IEEE Trans. on Speech and Audio Proc. 9 (2001)
Reynolds, D., Quatieri, T., Dunn, R.: Speaker Verification Using Adapted Gaussian Mixture Models. Digital Signal Proc. 10 (2000)
Bilmes, J.: Graphical Models and Automatic Speech Recognition. Mathematical Foundations of Speech and Language Proc., 191–235 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ribas, D., Villalba, J.A., Lleida, E., Calvo, J.R. (2010). Speaker Verification in Noisy Environment Using Missing Feature Approach. In: Bloch, I., Cesar, R.M. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2010. Lecture Notes in Computer Science, vol 6419. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16687-7_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-16687-7_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16686-0
Online ISBN: 978-3-642-16687-7
eBook Packages: Computer ScienceComputer Science (R0)