Abstract
In this paper, we propose a novel cepstrum normalization method based on the scoring procedure of order statistics for speech recognition in additive noise environments. The conventional methods normalize the mean and/or variance of the cepstrum, which results in an incomplete normalization of the probability density function (PDF). The proposed method fully normalizes the PDF of the cepstrum, providing an identical PDF between clean and noisy cepstrum. For the target PDF, the generalized Gaussian distribution is selected to consider various densities. In recognition phase, a table lookup method is devised in order to save computational costs. From the speaker-independent isolated-word recognition experiments, we show that the proposed method gives improved performance compared with that of the conventional methods, especially in heavy noise environments.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Furui, S.: Cepstral analysis technique for automatic speaker verification. IEEE Tr. on Acoust., Speech, Signal Process., ASSP 29, 254–272 (1981)
Viiki, O., Bye, D., Laurila, K.: A recursive feature vector normalization approach for robust speech recognition in noise. In: Proc. ICASSP, pp. 733–736 (1998)
Hsu, C.W., Lee, L.S.: Higher order cepstral moment normalization (HOCMN) for robust speech recognition. In: Proc. ICASSP, pp. 197–200 (2004)
David, H.A.: Order Statistics. John Wiley & Sons, NY (1981)
David, F.N., Johnson, N.L.: Statistical treatment of censored data, Part I. fundamental Formulae. Biometrica 41, 228–240 (1956)
Kassam, S.A.: Signal Detection in Non-Gaussian Noise. Springer, Heidelberg (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Suk, Y.H., Choi, S.H. (2011). A Cepstral PDF Normalization Method for Noise Robust Speech Recognition. In: Lin, S., Huang, X. (eds) Advances in Computer Science, Environment, Ecoinformatics, and Education. CSEE 2011. Communications in Computer and Information Science, vol 215. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23324-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-23324-1_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23323-4
Online ISBN: 978-3-642-23324-1
eBook Packages: Computer ScienceComputer Science (R0)