Intelligent Hearing Assistance Using Self-Organizing Feature Maps

  • Michael Hodges Oakland University Rochester, MI
  • Mohamed Zohdy Oakland University Rochester, MI
Keywords: self-organizing feature maps, Artificial Intelligence, machine learning, neural networks, pattern classification

Abstract

A novel hearing assistance system is proposed which classifies sounds and selectively tunes them according to the needs of the hearing impaired.  This differs from the usual hearing aids available today in that it uses computational intelligence to filter and tune sounds based on real life categorical classifications.  The system can significantly improve audibility for the hearing impaired, including bringing completely inaudible tones into audibility.  For classification a self-organizing feature map is used with a vector of sound features from the joint time-frequency domain.  The map is trained with input sounds until a map of neurons is clustered according to its these.  The resulting map is used to classify new sounds.  Based on this classification, a sound can be tuned to improve audibility for the hearing impaired.  Techniques proposed for audio output include gammatone frequency filtering, Fourier compression, low pass filtering, spectral subtraction, and an original algorithm to choose how to best boost the amplitude of deaf frequencies.

References

Loizou, P. C., Mimicking the human ear. IEEE Signal Processing Magazine, 1998. 15(5): p. 101-130.

Sottek, R., & Genuit, K., Models of signal processing in human hearing. AEUE - International Journal of Electronics and Communications, 2005. 59(3): p. 157-165.

Allen, J.. Short term spectral analysis, synthesis, and modification by discrete Fourier transform. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1977. 25(3): p. 235-238.

Bryant, T., Hodges, M., & Zohdy, M. Self-organizing maps applied to engine health diagnostics. International Journal of Computer and Information Technology, 2014 3(2): p. 205-211.

Abdel-Aty-Zohdy, H. S., & Zohdy, M. A., Neural networks for pattern discovery and optimization in signal processing and applications. , 1995. 1: p. 202-206 vol.1.

Bryant, T., & Zohdy, M.,. Noise signal identification by modified self-organizing maps. International Journal of Computer and Information Technology, 2014. 3(1): p. 48-53.

Chung, K., Killion, M. C., & Christensen, L. A., Ranking hearing aid input-output functions for understanding low-, conversational-, and high-level speech in multitalker babble. Journal of Speech, Language, and Hearing Research, 2007. 50(2): p. 304-322.

Cosentino, S., Falk, T., McAlpine, D., & Marquardt, T.,. Cochlear implant filterbank design and optimization: A simulation study. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 2014. 22(2): p. 347-353.

Couturier, M. M. Disambiguating words with self-organizing maps. Master’s Thesis, Massachusetts Institute of Technology, 2011.

Gan, R. Z., Wood, M. W., & Dormer, K. J., Human middle ear transfer function measured by double laser interferometry system. Otology & Neurotology : Official Publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology, 2004. 25(4): p. 423-435.

Ghaffari, R., Page, S. L., Farrahi, S., Sellon, J. B., & Freeman, D. M., Electrokinetic properties of the mammalian tectorial membrane. Proceedings of the National Academy of Sciences of the United States of America, 2013. 110(11): p. 4279-4284.

Gladston, A. R., Vijayalakshmi, P., & Thangavelu, N.. Improving speech intelligibility in cochlear implants using vocoder-centric acoustic models, 2012: p. 66-71.

Gonzalez, R., & Woods, R.. In McDonald M., Dworkin A. (Eds.), Digital image processing, 3rd edition ed2008, New Jersey: Pearson Education.

Kelly, F., Kelly, F., Harte, N., & Harte, N.. Auditory features revisited for robust speech recognition. 2010: p. 4456-4459.

Mayer, R., Aziz, T. A., & Rauber, A.. Visualising class distribution on self-organising maps. 2007: p. 359-368. Berlin, Heidelberg: Springer Berlin Heidelberg.

Ngamkham, W., Ngamkham, W., Sawigun, C., Sawigun, C., Hiseni, S., Hiseni, S., et al,. Analog complex gammatone filter for cochlear implant channels. 2010: p. 969-972.

Nsour, A., & Zohdy, M., Self organized learning applied to global positioning system (GPS) data. Proceedings of the 6th WSEAS International Conference on Signal, Speech, and Image Processing, Lisbon, Portugal. 2006.

Puengue, L., Liu, D., & Zohdy, M.. Modified self organizing feature maps for classification of mathematical curves. International Journal of Computer and Information Technology, 2013. 2(5), 972-973-980.

Purves, D., Augustine, G., Fitzpatrick, D., Katz, L., LaMantia, A., McNamara, J., et al., Neuroscience ed2001, Sunderland: Sinauer Associates.

Stekh, Y., Sardieh, F. M. E., & Lobur, M., Neural network based clustering algorithm. 2009: p. 168-169.

Su, M. C., & Chang, H. T., Fast self-organizing feature map algorithm. IEEE Transactions on Neural Networks / a Publication of the IEEE Neural Networks Council, 2000. 11(3): p. 721-733.

Vesanto, J., & Alhoniemi, E., Clustering of the self-organizing map. , 2000. 11 (3): p. 586-600.

Wernick, M. N., Yang, Y., Brankov, J. G., Yourganov, G., & Strother, S. C.,. Machine learning in medical imaging. IEEE Signal Processing Magazine, 2010. 27(4): p. 25-38.

Wheeler, D. E. Measurement of industrial hearing loss. Noise Control, 1955. 1(4), 9.

Yan, P., Suzuki, K., Wang, F., & Shen, D.,. Machine learning in medical imaging. Machine Vision and Applications, 2013. 24(7): p. 1327-1329.

Zhu, X., Zhang, L., Wei, J., & Zhou, S.,. Application of wavelets and principal component analysis to process quantitative feature extraction, 2008.

Published
2015-01-01