Abstract
The nature of spike coding of auditory signals is studied by comparing mean firing rate codes with conventional approaches in speech recognition tasks. Mean firing rate spike representations are problematic since most auditory nerve fibers are saturated at typical conversation levels. However, these problems are eased somewhat when it is considered that there are other nerve fibers (e.g. low spontaneous firing rate fibers) that could efficiently encode the information at each channel of the cochlea. We show that window-based, mean firing rate features can be used with a crude cochlea model to achieve the same level of performance as a conventional MFCC-based approach. These results assume that there are sufficient neurons available at each channel to average the randomness of the stochastic spike trains. Furthermore, we argue that the mean firing rate features could be augmented with timing cues for further performance improvement. ©2010 IEEE.
Recommended Citation
J. G. Harris and Y. Feng, "Mean Firing Rate Spike Representations For Speech Recognition," Iscas 2010 2010 IEEE International Symposium on Circuits and Systems Nano Bio Circuit Fabrics and Systems, pp. 517 - 520, article no. 5537579, Institute of Electrical and Electronics Engineers, Aug 2010.
The definitive version is available at https://doi.org/10.1109/ISCAS.2010.5537579
Department(s)
Electrical and Computer Engineering
International Standard Book Number (ISBN)
978-142445308-5
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
31 Aug 2010
