Abstract
Noise canceling is an adaptive interference filtering technique that has shown to be highly adventageous in many applications where fixed filters are not efficient. We present an experimental neuro-fuzzy inference system, based on the ANFIS architecture, which has been implemented with the objective to perform nonlinear adaptive noise cancellation from speech. The novelty of the system described in the present paper, with respect to our previus work, consists in a different set up, which requires two inputs with seven membership functions each, and uses a second order sinc function to generate the nonlinear distortion of the noise. This set up allows a better generalization to the system for learning the noise features. Indeed, the system was trained only once during few epochs, with a sample of babble noise, but it was able to clean speech sentences corrupted not only with the same noise, but also with car, traffic, and white noise. The average improvement, in terms of SNR, was 37 dB without further training, resulting in a great reduction of the computational time.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Widrow, B., Glover, J.R., McCool, J.M., et al.: Adaptive Noise Cancelling: Principles and Applications. IEEE Proceedings 63(12), 1692–1716 (1975)
Widrow, B., Stearns, S.D.: Adaptive Signal Processing. Prentice Hall, Englewood Cliffs (1985)
Simon, H.: Adaptive Filter Theory. Prentice Hall International, Upper Saddle River (1996)
Avendano, C., Hermansky, H.: On the Properties of Temporal Processing for Speech in Adverse Environments. In: Proceedings of 1997 Workshop on Applications of Signal Processing to Audio and Acoustics, Mohonk Mountain House, New Paltz, New York (1997)
Hermansky, H.: Analysis in Automatic Recognition of Speech. In: Chollet, G., et al. (eds.) Speech Processing, Recognition, and Artificial Neural Networks. Springer, London (1999)
Avendano, C.: Temporal Processing of Speech in a Time Feature Space, Ph.D. Dissertation, Oregon Graduate Institute of Science and Technology (April 1997)
Wan, E., Nelson, A.: Neural Dual Extended Kalman Filtering: Applications in Speech Enhancement and Monaural Blind Signal Separation. In: Principe, M., Giles, W. (eds.) Proceedings of the 1997 IEEE Workshop in Neural Networks for Signal Processing VII (1997)
Wan, E., Nelson, A.: Networks for Speech Enhancement. In: Handbook of Neural Networks for Speech Processing, Edited by Shingeru Katagiri, Artech House, Boston (1998)
Jang, J.-S.R., Sun, C.-T., Mizutani, E.: Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. Prentice Hall International, Upper Saddle River (1997)
Jang, J.-S.R.: ANFIS: Adaptive Network-based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics 23(03), 665–685 (1993)
Jang, J.-S.R.: Neuro-Fuzzy Modeling: Architectures, Analyses and Applications, Ph.D. Dissertation, University of California, Berkeley (July 1992)
Jang, J.-S.R., Sun, C.-T.: Neuro-Fuzzy Modeling and Control. The Proceedings of the IEEE 83, 378–405 (1995)
Lin, C.-T., George Lee, C.S.: Neural Fuzzy System: A Neuro-Fuzzy Synergism to Intelligent Systems. Prentice Hall, Upper Saddle River (1996)
Speaks, C.E.: Introduction to Sound: Acoustics for the Hearing and Speech Science. Singular Publishing Group Inc., San Diego (1997)
Esposito, A., Ezin, E.C., Reyes-Garcia, C.A.: A Nonlinear Adaptive System to Cancel Noise from Speech. In: WILF 1999 Proceedings, Genova, Italy (June 1999)
Esposito, A., Ezin, E.C., Reyes-Garcia, C.A.: Speech Noise Cancellation on a Neuro-Fuzzy System: Experimental Results. In: IEEE’s WISP 1999 Proceedings, Budapest, Hungary, pp. 342–347 (September 1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Esposito, A., Ezin, E.C., Reyes-Garcia, C.A. (2000). Designing a Fast Neuro-fuzzy System for Speech Noise Cancellation. In: Cairó, O., Sucar, L.E., Cantu, F.J. (eds) MICAI 2000: Advances in Artificial Intelligence. MICAI 2000. Lecture Notes in Computer Science(), vol 1793. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10720076_44
Download citation
DOI: https://doi.org/10.1007/10720076_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67354-5
Online ISBN: 978-3-540-45562-2
eBook Packages: Springer Book Archive