Research Repository

The representation of speech in a nonlinear auditory model: time-domain analysis of simulated auditory-nerve firing patterns

Brown, G and Juergens, T and Meddis, R and Robertson, M and Clark, N (2012) 'The representation of speech in a nonlinear auditory model: time-domain analysis of simulated auditory-nerve firing patterns.' In: UNSPECIFIED, (ed.) Proceedings of the 12th Annual Conference of the International Speech Communication Association 2011 (INTERSPEECH 2011). Curran Associates, 2464 - 2468. ISBN 9781618392701

[img]
Preview
Text
Brown_Interspeech_2011.pdf

Download (3MB) | Preview

Abstract

A nonlinear auditory model is appraised in terms of its ability to encode speech formant frequencies in the fine time structure of its output. It is demonstrated that groups of model auditory nerve (AN) fibres with similar interpeak intervals accurately encode the resonances of synthetic three-formant syllables, in close agreement with physiological data. Acoustic features are derived from the interpeak intervals and used as the input to a hidden Markov model-based automatic speech recognition system. In a digits-in-noise recognition task, interval-based features gave a better performance than features based on AN firing rate at every signal-to-noise ratio tested.

Item Type: Book Section
Additional Information: Proceedings of the 12th Annual Conference of the International Speech Communication Association 2011 (INTERSPEECH 2011) 27-31 August 2011, Florence, Italy.
Uncontrolled Keywords: auditory model; time interval; automatic speech recognition
Subjects: Q Science > QP Physiology
Divisions: Faculty of Science and Health > Psychology, Department of
Depositing User: Ray Meddis
Date Deposited: 28 Mar 2013 10:17
Last Modified: 17 Aug 2017 18:01
URI: http://repository.essex.ac.uk/id/eprint/5939

Actions (login required)

View Item View Item