Summary
The algorithms stemming from the rough-neural computing approach were applied to digital acquisition of audio signals with regard to automatic localization of sound sources in the presence of noise and a parasite echo. The application of neural networks to the automatic detection of the sound arrival direction was tested first; then, it was followed by some experiments employing rough sets, and finally the rough-neural approach to this problem solving was examined. The output of each algorithm tested was supposed to provide information about the direction of arriving sound. In the rough-neural algorithm, the result of its action can also be available in the form of words defining the direction of arriving sound. Some details of the engineered systems and results of their experimental verification are compared and discussed.
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
B. Berdugo, M.A. Doron, J. Rosenhouse, and H. Azhari. On direction finding of an emitting source from time delays.Journal of the Acoustical Society of America106: 3355–3363, 1999.
M. Bodden. Modeling human sound-source localization and the cocktail-party-effect.Acta Acustica 1:43–55,1993.
M.S. Brandstein. A pitch-based approach to time-delay estimation of reverberant speech. InProceedings of the IEEE Workshop on Applications of Signal Processing to Audio and AcousticsMohonk, New Paltz, NY, 1997.
W.-F. Chang, M.W. Mak. A conjugate gradient learning algorithm for recurrent neural networks.Neurocomputing: An International Journal24: 173–189, 1999.
S.-J. Cheat, S.-H. Lin. An adaptive time delay estimation with direct computation formula.Journal of the Acoustical Society of America96: 811–820,1994.
J. Czerniawski.The Verification of New Algorithms for Identifying Sound Source Position and Sound Acquisition Methods Based on Spatial Filtering.Masters Thesis, Technical University of Gdansk, 2001 (in Polish).
A. Czyzewski, R. Krolikowski. Neuro-rough control of masking thresholds for audio signal enhancement.Neurocomputing: An International Journal36: 5–27, 2001.
M.S. Datum, F.Palmieri, A. Moiseff. An artificial neural network for sound localization using binaural cues.Journal of the Acoustical Society of America100: 3372–3383, 1996.
S.P. Day, M.R. Davenport. Continuous-time temporal back-propagation with adaptable time delays. InIEEE Transactions on Neural Networks4: 348–354, 1993. 540 A. Czyzewski
J.L. Elman. Finding structure in time.Cognitive Science14: 179–211, 1990.
M.W. Goudreau, C.L. Giles, S. T. Chakradhar, D. Chen. First-order vs. second-order single layer recurrent neural networks.IEEE Transactions on Neural Networks5: 511–518, 1994.
M.W. Goudreau, C.L. Giles. Using recurrent neural networks to learn structure of interconnection networks.IEEE Transactions on Neural Networks8: 793–820, 1995.
M.W. Hartmann. How we localize sound.Physics Today 11:24–29, 1999.
B.G. Horne, C.L. Giles. An experimental comparison of recurrent neural networks. In G. Tesauro,D. Touretzky, T. Leen, editorsAdvances in Neural Information Processing SystemsVol. 7, 697–705, MIT Press, Cambridge, MA, 1995.
G. Jacovitti, G. Scarano. Discrete time techniques for time delay estimation. InIEEE Transactions on Signal Processing41: 525–533, 1993.
F. Khalil, J.P. Lullien, A. Gilloire. Microphone array for sound pickup in teleconference systems.Journal of the Audio Engineering Society42: 691–700, 1994
A. Czyzewski, B. Kostek, J. Lasecki. Microphone array for improving speech intelligibility. InProceedings of the 20th Tonmeistertagung International Convention on Sound Design428–434, Karlsruhe, 1998.
B. Kostek, A. Czyzewski, J. Lasecki. Spatial filtration of sound for multimedia systems. InProceedings of the Copenhagen Workshop on Multimedia Signal Processing (MMSP’99)(CD-ROM), 209–213, IEEE Signal Processing Society, Piscataway, NJ, 1999.
B. Kostek, A. Czyzewski, J. Lasecki. Computational approach to spatial filtering. InProceedings of the 7th European Congress on Intelligent Techniques and Soft Computing (EUFIT’99) (CD-ROM)242, Aachen, 1999.
J. Lasecki, B. Kostek, A. Czyzewski. Neural network-based spatial filtration of sound. InProceedings of the 106th Audio Engineering Society ConventionPreprint No. 4918, Munich, 1999.
T. Lin, C.L. Giles, B.G. Horne, S.Y. Kung. A delay damage model selection algorithm for NARX neural networks. InIEEE Transactions on Signal Processing(special issue on neural networks), 11: 2719–2730,1997.
T. Lin, B.G. Horne, P. Tino, C.L. Giles. Learning long-term dependencies in NARX recurrent neural networks. InIEEE Transactions on Neural Networks7: 1329–1351, 1996.
Y. Mahieux, G. le Tourneur, A. Saliou. A microphone array for multimedia workstations.Journal of the Audio Engineering Society44: 365–372, 1996.
S. Fahlman. An empirical study of learning speed in back-propagation networks. Technical Report CMU-CS-88–162 of Carnegie Mellon University, Pittsburgh, PA, 1988.
M. Riedmiller, H. Braun. A direct adaptive method for faster backpropagation learning: The RPROP Algorithm. InProceedings of the IEEE International Conference on Neural Networks586–591, San Francisco, 1993.
H.T. Siegelmann, B.G. Horne, C.L. Giles. Computational capabilities of recurrent NARX neural networks. InIEEE Transactions on Systems Man and CyberneticsPart B: Cybernetics, 2: 208–228, 1997.
J.P.F. Sum, W.-K. Kan, G.H. Young. A note on the equivalence of NARX and RNN.Neural Computing and Applications8: 33–39, 1999.
M. Szczerba. Sound Source Localization Based on Rough-Set Approach. Technical Report, Sound & Vision Engineering Department, Technical University Gdansk, 2001.
H. Wang, P. Chu. Voice source localization for automatic camera pointing system in videoconferencing. InProceedings of the IEEE Workshop on Applications of Signal Processing to Audio and AcousticsMohonk, New Paltz, NY, 1997.
R.J. Williams, D. Zipser. A learning algorithm for continually running fully recurrent neural networks.Neural Computation 1:270–280, 1989.
M. Zhang, M.H. Er. An alternative algorithm for estimating and tracking talker location by microphone arrays.Journal of the Audio Engineering Society44: 729–736, 1996.
I. Ziskind, M. Wax. Maximum likelihood localization of multiple sources by alternating projection. InIEEE Transactions on Acoustics Speech and Signal Processing36: 1553–1560, 1988.
J.M. Zurada.Introduction to Artificial Neural Networks.West, St. Paul, MN, 1992.
A. Øhre.Discernibility and Rough Sets in Medicine: Tools and Applications.Ph.D.Dissertation, NTNU Report 1999: 133, IDI Report (1999)Department of Computer and Information Science, Norwegian University of Science and Technology, Trondheim, 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Czyżewski, A. (2004). Intelligent Acquisition of Audio Signals, Employing Neural Networks and Rough Set Algorithms. In: Pal, S.K., Polkowski, L., Skowron, A. (eds) Rough-Neural Computing. Cognitive Technologies. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18859-6_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-18859-6_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-62328-8
Online ISBN: 978-3-642-18859-6
eBook Packages: Springer Book Archive