Perceptual Properties of Current Speech Recognition Technology
Authors:
- 23 July 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 101 (9) , 1968-1985
Abstract
In recent years, a number of feature extraction procedures for automatic speech recognition (ASR) systems have been based on models of human auditory processing, and one often hears arguments in favor of implementing knowledge of human auditory perception and cognition into machines for ASR. This paper takes a reverse route, and argues that the engineering techniques for automatic recognition of speech that are already in widespread use are often consistent with some well-known properties of the human auditory system.Keywords
Funding Information
- National Science Foundation (IIS-I0916918)
This publication has 86 references indexed in Scilit:
- Robust auditory-based speech processing using the average localized synchrony detectionIEEE Transactions on Speech and Audio Processing, 2002
- Data-Driven Temporal Filters and Alternatives to GMM in Speaker VerificationDigital Signal Processing, 2000
- On the effects of short-term spectrum smoothing in channel normalizationIEEE Transactions on Speech and Audio Processing, 1997
- Effects of spectral contrast on perceptual compensation for spectral-envelope distortionThe Journal of the Acoustical Society of America, 1996
- RASTA processing of speechIEEE Transactions on Speech and Audio Processing, 1994
- Perceptual linear predictive (PLP) analysis of speechThe Journal of the Acoustical Society of America, 1990
- Application of an auditory model to speech recognitionThe Journal of the Acoustical Society of America, 1989
- Linear prediction on a warped frequency scaleThe Journal of the Acoustical Society of America, 1980
- On the front cavity resonance and its possible role in speech perceptionThe Journal of the Acoustical Society of America, 1975
- Automatic Recognition of Spoken DigitsThe Journal of the Acoustical Society of America, 1952