Abstract

Present day commercial automatic speech recognition (ASR) systems still pale in comparison to the human ability to recognize speech. For decades, people tried to mimic biology for machine recognition tasks and ASR is no exception. Widely used and accepted Mel Frequency Cepstral Coefficients, for example, try to develop better filter banks by looking at the distribution of the hair cells along the basilar membrane. However, all these approaches stem only from topological and anatomical considerations. This research proposes to take this biological inspiration one step further by imitating some of the dynamical computation of our auditory system via describing a biologically plausible algorithm that exclusively utilizes spikes in both the feature extraction and recognition stages. The prototype biological system is demonstrated on voiced phonemes and preliminary results show competitive recognition performance on a vowel dataset in the presence of noise. © 2006 IEEE.

Department(s)

Electrical and Computer Engineering

International Standard Book Number (ISBN)

978-142440173-4

International Standard Serial Number (ISSN)

1548-3746

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

01 Dec 2006

Share

 
COinS