Abstract
In this paper, we propose a noise reduction method based on non-negative matrix factorization (NMF) for noise-robust automatic speech recognition (ASR). Most noise reduction methods applied to ASR front-ends have been developed for suppressing background noise that is assumed to be stationary rather than non-stationary. Instead, the proposed method attenuates non-target noise by a hybrid approach that combines a Wiener filtering and an NMF technique. This is motivated by the fact that Wiener filtering and NMF are suitable for reduction of stationary and non-stationary noise, respectively. It is shown from ASR experiments that an ASR system employing the proposed approach improves the average word error rate by 11.9%, 22.4%, and 5.2%, compared to systems employing the two-stage mel-warped Wiener filter, the minimum mean square error log-spectral amplitude estimator, and NMF with a Wiener post-filter, respectively.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Wu, J., Droppo, J., Deng, L., Acero, A.: A noise-robust ASR front-end using Wiener filter constructed from MMSE estimation of clean speech and noise. In: IEEE Workshop on ASRU, pp. 321–326 (2003)
Choi, H.C.: Noise robust front-end for ASR using spectral subtraction, spectral flooring and cumulative distribution mapping. In: 10th Australian Int. Conf. on Speech Science and Technology, pp. 451–456 (2004)
Ephraim, Y., Malah, D.: Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Trans. Acoust. Speech Signal Process. 33(2), 443–445 (1985)
Agarwal, A., Cheng, Y.M.: Two-stage mel-warped Wiener filter for robust speech recognition. In: IEEE Workshop on ASRU, pp. 67–70 (1999)
Lee, S.J., Kang, B.O., Jung, H.Y., Lee, Y.K., Kim, H.S.: Statistical model-based noise reduction approach for car interior applications to speech recognition. ETRI Journal 32(5), 801–809 (2010)
Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)
Wilson, K.K., Raj, B., Smaragdis, R., Divakaran, A.: Speech denoising using non-negative matrix factorization with priors. In: ICASSP, pp. 4029–4032 (2008)
Kim, S.M., Kim, H.K., Lee, S.J., Lee, Y.K.: Noise robust speech recognition based on a non-negative matrix factorization. In: Inter-noise 2011 (2011)
Virtanen, T.: Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans. Speech Audio Process. 15(3), 1066–1074 (2007)
Malah, D., Cox, R., Accardi, A.J.: Tracking speech-presence uncertainty to improve speech enhancement in nonstationary noise environments. In: ICASSP, pp. 789–792 (1999)
Sohn, J., Kim, N.S., Sung, W.: statistical model-based voice activity detection. IEEE Signal Process. Lett. 6(1), 1–3 (1999)
Lee, D.D., Seung, H.S.: Algorithms for nonnegative matrix factorization. In: Adv. Neural Inform. Process. Sys., vol. 13, pp. 556–562 (2000)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kim, S.M., Park, J.H., Kim, H.K., Lee, S.J., Lee, Y.K. (2012). Non-negative Matrix Factorization Based Noise Reduction for Noise Robust Automatic Speech Recognition. In: Theis, F., Cichocki, A., Yeredor, A., Zibulevsky, M. (eds) Latent Variable Analysis and Signal Separation. LVA/ICA 2012. Lecture Notes in Computer Science, vol 7191. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-28551-6_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-28551-6_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-28550-9
Online ISBN: 978-3-642-28551-6
eBook Packages: Computer ScienceComputer Science (R0)