Abstract
In this paper a framework of the heterogeneous system for an adaptive classification of multivariate numerical data is proposed. Considered data characterize the dynamics of the simulated responses of auditory nerve fibers as probability that represents the average of the ensemble for acoustic signals. The possibility to classify sound stimuli by means of analysis of the responses of the auditory nerve for the fibers with high and low spontaneous rates is examined. The aim of the study was to develop and implement a method for an adaptive pattern recognition in limited a priori information about their number and structure. The proposed model architecture consists of several units that generalize basic stages of a perceptual process that in turn corresponds neuro-symbolic information processing approach to the machine perception problem. Proposed method combines the advantages of the self-organizing maps and the radial basic function networks. This combination leads to a hybrid learning approach, which allow to provide the automatic classification of unlabeled data. According to the obtained results, the proposed approach showed better accuracy for several complex benchmark tests as well as for pure tones recognition by means of simulated auditory nerve fibers responses compared to k-means and single-linkage unsupervised classification strategies.
Similar content being viewed by others
REFERENCES
Kaas, J.H., Topographic maps are fundamental to sensory processing, Brain Res. Bull., 1997, vol. 44, pp. 107–112.
Velik, R., Towards human-like machine perception 2.0, Int. Rev. Comput. Software, 2010, vol. 5, no. 4, pp. 476–488.
Rattay, F., Mladenka, A., and Pontes, J., Classifying auditory nerve patterns with neural nets: A modeling study with low level signals, Simul. Pract. Theory, 1998, vol. 6, pp. 493–503.
Bibikov, N.G. and Grigor’ev, D.Y., The use of neural networks for the determination of the signal modulation frequency from the firing activity pattern in the auditory neurons of the frog, Acoust. Phys., 2007, vol. 53, no. 6, pp. 751–761.
Rattay, F., Improving hearing performance using natural auditory coding strategies, in Biomimetics—Materials, Structures and Processes. Biological and Medical Physics, Biomedical Engineering, Berlin, Heidelberg: Springer, 2011, pp. 249–261.
Lublinskaya, V.V., Is hearing necessary for automatic speech recognition?, Sens. Sist., 2009, vol. 23, no. 4, pp. 275–282.
Speech Separation by Humans and Machines, Divenyi, P., Ed., Kluwer Academic, 2005.
Machine Audition: Principles, Algorithms and Systems, Wang, W., Ed., IGI Global Press, 2010.
Lyon, R.F., Human and Machine Hearing: Extracting Meaning from Sound, Cambridge University Press, 2017.
Pao, Y.H., Adaptive Pattern Recognition and Neural Networks, Massachusetts: Addison-Wesley Publishing, 1989.
Kohonen, T., Self-Organizing Maps, Springer, 2001, 3rd ed.
Kohonen, T., Self-organized formation of topologically correct feature maps, Biol. Cybern., 1982, vol. 43, pp. 59–69.
Attik, M., Bougrain, L., and Alexandre, F., Self-organizing map initialization, Artificial Neural Networks: Biological Inspirations—ICANN 2005; Lect. Notes Comput. Sci., 2005, vol. 3696, pp. 357–362.
Haykin, S., Kernel methods and radial-basis function networks, in Neural Networks and Learning Machines, Prentice Hall, 2009, 3rd ed., pp. 230–267.
Yakovenko, A.A. and Malykhina, G.F., Text-independent speaker recognition using radial basis function network, Lect. Notes Comput. Sci., 2016, vol. 9719, pp. 74–81.
Schwenker, F., Kestler, H., and Palm, G., Three learning phases for radial-basis-function networks, Neural Networks, 2001, vol. 14, nos. 4–5, pp. 439–458.
Meddis, R. and Lopez-Poveda, E.A., Auditory periphery: From pinna to auditory nerve, in Computational Models of the Auditory System, Springer Handbook of Auditory Research, Boston, MA: Springer, 2010, vol. 35, pp. 7–38.
Meddis, R., Lecluyse, W., Clark, N.R., Jürgens, T., Tan, C.M., Panda, M.R., and Brown, G.J., A computer model of the auditory periphery and its application to the study of hearing, in Basic Aspects of Hearing: Physiology and Perception, Springer, 2013, vol. 787, pp. 11–20.
Pölzlbauer, G., Survey and comparison of quality measures for self-organizing maps, Proc. of the Fifth Workshop on Data Analysis, 2004, pp. 67–82.
Vesanto, J. and Alhoniemi, E., Clustering of the self-organizing map, IEEE Trans. Neural Networks, 2000, vol. 11, no. 2, pp. 586–600.
Vesanto, J. and Sulkava, M., Distance matrix based clustering of the self-organizing map, in Proc. of the International Conference on Artificial Neural Networks, 2002, pp. 951–956.
Ultsch, A., Self-organizing neural networks for visualization and classification, in Information and Classification, Berlin: Springer, 1993, pp. 307–313.
Ultsch, A., Clustering with SOM: U*C, Proc. Workshop on Self-Organizing Maps, Paris, 2005, pp. 75–82.
Yakovenko, A.A. and Malykhina, G.F., Bio-inspired approach for automatic speaker clustering using auditory modeling and self-organizing maps, Procedia Comput. Sci., 2018, vol. 123, pp. 547–552.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Yakovenko, A.A. A Hybrid Learning Approach for Adaptive Classification of Acoustic Signals Using the Simulated Responses of Auditory Nerve Fibers. Opt. Mem. Neural Networks 28, 118–128 (2019). https://doi.org/10.3103/S1060992X19020048
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X19020048