Evaluation of wains as a classifier for automatic speech recognition

Rosemary T. Salaja, Ronan Flynn, Michael Russell

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

This paper introduces a new back-end classifier for a speech recognition system that is based on artificial life (ALife). The ALife species being used for classification purposes are called wains, which were developed using the Créatúr framework. The speech recognition task used in the evaluation of the new classifier is that of isolated digit recognition. Performance of the proposed back-end classifier is benchmarked for comparison purposes against a hidden Markov model (HMM)-based classifier. Mel frequency cepstral coefficients extracted from the speech by a front-end processor are used by the two back-ends for classification of the speech utterances. In tests carried out to date, the performance of the proposed classifier falls short of the performance of the HMM-based classifier. However, the results suggest that with further training the recognition accuracy of the proposed classifier can be significantly improved.

Original languageEnglish
Title of host publication2015 26th Irish Signals and Systems Conference, ISSC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467369749
ISBN (Print)9781467369749
DOIs
Publication statusPublished - 21 Jul 2015
Event26th Irish Signals and Systems Conference, ISSC 2015 - Carlow, Ireland
Duration: 24 Jun 201525 Jun 2015

Publication series

Name2015 26th Irish Signals and Systems Conference, ISSC 2015

Conference

Conference26th Irish Signals and Systems Conference, ISSC 2015
Country/TerritoryIreland
CityCarlow
Period24/06/1525/06/15

Keywords

  • Artificial Life
  • Automatic Speech Recognition
  • Créatúr
  • Wains

Fingerprint

Dive into the research topics of 'Evaluation of wains as a classifier for automatic speech recognition'. Together they form a unique fingerprint.

Cite this