Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

A Speech Recognition System Using Both Auditory and Afferent Pathway Signal Processing

Eliathamby Ambikairajah (1), Owen Friel (1), William Millar (2)

(1) Department of Electronic Engineering, Regional Technical College, Athlone, Ireland
(2) British Telecom Laboratories, Ipswich, England

This paper describes an implementation of a speech recognition system using a neural network, originally proposed by Kurogi [1], which is based on findings from the auditory mechanism, including both auditory signal processing and afferent pathway signal processing. A design procedure for a multi-rate cochlear model is described. The model uses a cascade of constant-Q filters. The model covers the bandwidth from 75Hz to 3.55kHz and is used as a pre-processor to the neural network. The neural network reproduces response patterns typical in the auditory system. The network does not use any time-warping and makes no use of the back-propagation algorithm for training. Preliminary results are presented for speaker independent speech recognition experiments carried out using a subset of the British Telecom Sl-Connex database.

Full Paper

Bibliographic reference.  Ambikairajah, Eliathamby / Friel, Owen / Millar, William (1994): "A speech recognition system using both auditory and afferent pathway signal processing", In ICSLP-1994, 1487-1490.