Improving The Filter Bank Of A Classic Speech Feature Extraction Algorithm

Author

Mark D. Skowronski
John G. Harris, Missouri University of Science and TechnologyFollow

Abstract

The most popular speech feature extractor used in automatic speech recognition (ASR) systems today is the mel frequency cepstral coefficient (mfcc) algorithm. Introduced in 1980, the filter bank-based algorithm eventually replaced linear prediction cepstral coefficients (Ipcc) as the premier front end, primarily because of mfcc's superior robustness to additive noise, However, mfcc does not approximate the critical bandwidth of the human auditory system. We propose a novel scheme for decoupling filter bandwidth from other filter bank parameters, and we demonstrate improved noise robustness over three versions of mfcc through HMM-based experiments with the English digits in various noise environments.

Recommended Citation

M. D. Skowronski and J. G. Harris, "Improving The Filter Bank Of A Classic Speech Feature Extraction Algorithm," Proceedings IEEE International Symposium on Circuits and Systems, vol. 4, pp. IV281 - IV284, Institute of Electrical and Electronics Engineers, Jul 2003.

Department(s)

Electrical and Computer Engineering

International Standard Serial Number (ISSN)

0271-4310

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

14 Jul 2003