Sound Recognition System Using Spiking and MLP Neural Networks

详细信息    查看全文

• 关键词：Neuromorphic auditory hardware ; Address ; Event representation ; Spiking neural networks ; Sound recognition ; Spike signal processing
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9887
• 期：1
• 页码：363-371
• 全文大小：821 KB
• 参考文献：1.Pickles, J.O.: An Introduction to the Physiology of Hearing. Emerald, London (2012)
  2.Guerrero-turrubiates, J.J., Gonzalez-reyna, S.E., Ledesma-orozco, S.E., Avina-cervantes, J.G.: Pitch estimation for musical note recognition using artificial neural networks. In: International Conference on Electronics, Communications and Computers (CONIELECOMP), pp. 53–58 (2014)
  3.Nielsen, A.B., Hansen, L.K., Kjems, U.: Pitch based sound classification. In: 2006 Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), vol. 3, pp. 788–791 (2006)
  4.Pishdadian, F., Nelson, J.K.: On the transcription of monophonic melodies in an instance-based pitch classification scenario. In: Proceedings of 2013 IEEE Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2013, pp. 222–227 (2013)
  5.Iwasa, K., Kugler, M., Kuroyanagi, S., Iwata, A.: A sound localization and recognition system using pulsed neural networks on FPGA. In: International Joint Conference on Neural Networks, IJCNN 2007, pp. 902–907. IEEE, August 2007
  6.Newton, M.J., Smith, L.S.: Biologically-inspired neural coding of sound onset for a musical sound classification task. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1386–1393 (2011)
  7.Liu, S.C.: Event-Based Neuromorphic Systems. Wiley (2015)
  8.Waibel, A., Hanazawa, T., Hinton, G., Shiano, K., Lang, K.J.: Phoneme recognition using time-delay neural networks. IEEE Trans. Acousti. Speech Sig. Process. 37(3), 328–339 (1989)CrossRef
  9.Gerstner, W., Kistler, W.M.: Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press, Cambridge (2002)CrossRef MATH
  10.Robert, A., Eriksson, J.L.: A composite model of the auditory periphery for simulating responses to complex sounds. J. Acoust. Soc. Am. 106(4), 1852–1864 (1999)CrossRef
  11.Eriksson, J.L., Robert, A.: The representation of pure tones and noise in a model of cochlear nucleus neurons. J. Acoust. Soc. Am. 106(4), 1865–1879 (1999)CrossRef
  12.Jaeger, H.: Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the “echo state network” approach. GMD Report 159, German National Research Center for Information Technology (2002)
  13.Mendes, J.A., Robson, R.R., Labidi S., Barros A.K.: Subvocal Speech recognition based on EMG signal using independent component analysis and neural network MLP. In: Congress on Image and Signal Processing, CISP 2008, vol. 1, pp. 221–224 (2008)
  14.Indiveri, G., Chicca, E., Douglas, R.: A VLSI array of low-power spiking neurons and bistables synapses with spike-timig dependant plasticity. IEEE Trans. Neural Netw. 17(1), 211–221 (2006)CrossRef
  15.Thorpe, S.J., Brilhault, A., Perez-Carrasco, J.A.: Suggestions for a biologically inspired spiking retina using order-based coding. In: 2010 IEEE International Symposium on Circuits and Systems Nano-Bio Circuit Fabrics and Systems, ISCAS 2010, pp. 265–268 (2010)
  16.Mahowald, M.: VLSI analogs of neuronal visual processing: a synthesis of form and function, Ph.D. dissertation, California Institute of Technology, Pasadena (1992)
  17.Boahen, K.A.: Communicating Neuronal Ensembles between Neuromorphic Chips. Neuromorphic Systems. Kluwer Academic Publishers, Boston (1998)
  18.Lyon, R.F., Mead, C.: An analog electronic cochlea. IEEE Trans. Acoust. Speech Sig. Process. 36, 1119–1134 (1988)CrossRef MATH
  19.Wen, B.: Boahen, K.A silicon cochlea with active coupling. IEEE Trans. Biomed. Circ. Syst. 3, 444–455 (2009)CrossRef
  20.Hamilton, T.J., Jin, C., van Schaik, A., Tapson, J.: An active 2-d silicon cochlea. IEEE Trans. Biomed. Circ. Syst. 2, 30–43 (2008)CrossRef
  21.Liu, S-C., Van Schaik, A., Minch, B.A., Delbruck, T.: Event-based 64-channel binaural silicon cochlea with Q enhancement mechanisms. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS), 30 May−2 June 2010, pp. 2027–2030 (2010)
  22.Leong, M.P., Jin, C., Leong, P.: An FPGA-based electronic cochlea. EURASIP J. Appl. Sig. Process. 2003(7), 629–638 (2003)CrossRef
  23.Dundur, R., Latte, M.V., Kulkarni, S.Y., Venkatesha, M.K.: Digital filter for cochlear implant implemented on a field-programmable gate array. Int. J. Electr. Comput. Energ. Electron. Commun. Eng. 2(7), 468–472 (2008)
  24.Thakur, C.S., Hamilton, T.J., Tapson, J., van Schaik, A., Lyon, R.F.: FPGA Implementation of the CAR model of the Cochlea. In: IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1853−1856 (2014)
  25.Domínguez-Morales, M., Jimenez-Fernandez, A., Cerezuela-Escudero, E., Paz-Vicente, R., Linares-Barranco, A., Jimenez, G.: On the designing of spikes band-pass filters for FPGA. In: Honkela, T. (ed.) ICANN 2011, Part II. LNCS, vol. 6792, pp. 389–396. Springer, Heidelberg (2011)CrossRef
  26.Jimenez-Fernandez, A., Linares-Barranco, A., Paz-Vicente, R., Jiménez, G., Civit, A.: Building blocks for spike-based signal processing. In: International Joint Conference on Neural Networks, IJCNN, pp. 1–8 (2010)
  27.Gomez-Rodriguez, F., Paz, R., Miro, L., Linares-Barranco, A., Jimenez, G., Civit, A.: Two hardware implementations of the exhaustive synthetic AER generation method. In: Cabestany, J., Prieto, A.G., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 534–540. Springer, Heidelberg (2005)CrossRef
  28.Cerezuela-Escudero, E., Dominguez-Morales, M.J., Jiménez-Fernández, A., Paz-Vicente, R., Linares-Barranco, A., Jiménez-Moreno, G.: Spikes monitors for FPGAs, an experimental comparative study. In: Rojas, I., Joya, G., Gabestany, J. (eds.) IWANN 2013, Part I. LNCS, vol. 7902, pp. 179–188. Springer, Heidelberg (2013)CrossRef
  29.Rios-Navarro, A., Jimenez-Fernandez, A., Cerezuela-Escudero, E., Rivas, M., Jimenez, G., Linares-Barranco, A.: Live demostration: real-time motor rotation frequency detection by spike-based visual and auditory sensory fusion on AER and FPGA. In: Wermter, S., Weber, C., Duch, W., Honkela, T., Koprinkova-Hristova, P., Magg, S., Palm, G., Villa, A.E.P. (eds.) ICANN 2014. LNCS, vol. 8681, pp. 847–848. Springer, Switzerland (2014)
  30.Cerezuela-Escudero, E., Jimenez-Fernandez, A., Paz-Vicente, R., Dominguez-Morales, M., Linares-Barranco, A., Jimenez-Moreno, G.: Musical notes classification with Neuromorphic Auditory System using FPGA and a Convolutional Spiking Network. In: Proceedings of the 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1−7 (2015)
  31.Lass, N.: Contemporary Issues in Experimental Phonetics. Elsevier (2012)
  
• 作者单位：Elena Cerezuela-Escudero (16)
  Angel Jimenez-Fernandez (16)
  Rafael Paz-Vicente (16)
  Juan P. Dominguez-Morales (16)
  Manuel J. Dominguez-Morales (16)
  Alejandro Linares-Barranco (16)
  
  16. Robotic and Technology of Computers Lab, Department of Architecture and Technology of Computers, University of Seville, Seville, Spain
  
• 丛书名：Artificial Neural Networks and Machine Learning – ICANN 2016
• ISBN：978-3-319-44781-0
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9887

文摘

In this paper, we explore the capabilities of a sound classification system that combines a Neuromorphic Auditory System for feature extraction and an artificial neural network for classification. Two models of neural network have been used: Multilayer Perceptron Neural Network and Spiking Neural Network. To compare their accuracies, both networks have been developed and trained to recognize pure tones in presence of white noise. The spiking neural network has been implemented in a FPGA device. The neuromorphic auditory system that is used in this work produces a form of representation that is analogous to the spike outputs of the biological cochlea. Both systems are able to distinguish the different sounds even in the presence of white noise. The recognition system based in a spiking neural networks has better accuracy, above 91 %, even when the sound has white noise with the same power.