Better analysis for automatic speech recognition

Authors

  • Douglas O'Shaughnessy INRS-Telecommunications, EMT, University of Quebec, 800 de la Gauchetiere west, Montreal, Que., H5A 1K6, Canada

Keywords:

Acoustics, Fast Fourier transforms, Matrix algebra, Microphones, Automatic speech recognition (ASR)

Abstract

An efficient automatic speech recognition (ASR) analysis method was studied. An ideal robust ASR should decode speech from all speakers of a language and with different microphones and transmission channels. Various advantages of this method are: it is an automatic and effcient method; actual ASR results that appear to be better than with some other methods extensively examined in the past like basic linear predictive coding (LPC) or a filter bank.

Additional Files

Published

2002-09-01

How to Cite

1.
O’Shaughnessy D. Better analysis for automatic speech recognition. Canadian Acoustics [Internet]. 2002 Sep. 1 [cited 2024 Mar. 28];30(3):148-9. Available from: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/1498

Issue

Section

Proceedings of the Acoustics Week in Canada

Most read articles by the same author(s)