Abstract
Statistical speech enhancement methods often rely on a set of assumptions, like gaussianity of speech and noise processes or perfect knowledge of their parameters, that are not fully met in reality. Recent advancements have shown the potential improvement in speech enhancement obtained by employing supergaussian speech models conditioned on the estimated signal to noise ratio. In this paper we derive a supergaussian model for speech enhancement in which both speech and noise priors are assumed to be complex Gaussian mixture models. We introduce as well a method for the computation of the noise prior based on the noise variance estimator used. Finally, we compare the developed estimators with the conventional Ephraim-Malah filters in the context of robust automatic speech recognition.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
MCAulay, R.J., Malpass, L.M.: Speech enhancement Using a Soft-Decision Noise Suppression Filter. IEEE Trans. ASSP 28(2), 137–145 (1980)
Ephraim, Y., Malah, D.: Speech enhancement using a minimum mean-square error short-time amplitude estimator. IEEE Trans. ASSP 32(6), 1109–1121 (1984)
Ephraim, Y., Malah, D.: Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Trans. ASSP 33(2), 443–445 (1985)
Martin, R.: Speech enhancement using MMSE short time spectral estimation with gamma distributed speech priors. IEEE Int. Conf. Acoustics, Speech, Signal Processing 1, 253–256 (2002)
Cohen, I.: Noise Spectrum Estimation in Adverse Environments: Improved Minima controlled Recursive Averaging. IEEE Trans. ASSP 11(5), 466–475 (2003)
Lotter, T., Vary, P.: Speech Enhancement by MAP Spectral Amplitude Estimation Using a Super-Gaussian SpeechModel. EURASIP Journal on Applied Signal Processing 7, 1110–1126 (2005)
Ephraim, Y., Cohen, I.: Recent advancements in Speech Enhancement. In: The Electrical Engineering Handbook. CRC Press, Boca Raton (2005)
Erkelens, J., Hendriks, R., Heusdens, R., Jensen, J.: Minimum Mean-Square Error Estimation of Discrete Fourier Coefficients With Generalized Gamma Priors. IEEE Trans ASSP 15, 1741–1752 (2007)
Erkelens, J.S.: Speech Enhancement based on Rayleigh mixture modeling of Speech Spectral Amplitude Distributions. In: Proc. EUSIPCO 2007, pp. 65–69 (2007)
Hirsch, G.: Aurora-5 Experimental Framework for the Performance Evaluation of Speech Recognition in Case of a Hands-free Speech Input in Noisy Environments (2007)
Astudillo, R.F., Kolossa, D., Orglmeister, R.: Accounting for the Uncertainty of Speech Estimates in the Complex Domain for Minimum Mean Square Error Speech Enhancement. In: Proc. Interspeech, pp. 2491–2494 (2009)
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
Astudillo, R.F., Hoffmann, E., Mandelartz, P., Orglmeister, R. (2010). Speech Enhancement for Automatic Speech Recognition Using Complex Gaussian Mixture Priors for Noise and Speech. In: Solé-Casals, J., Zaiats, V. (eds) Advances in Nonlinear Speech Processing. NOLISP 2009. Lecture Notes in Computer Science(), vol 5933. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-11509-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-11509-7_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-11508-0
Online ISBN: 978-3-642-11509-7
eBook Packages: Computer ScienceComputer Science (R0)