Bispectral Gammatone Cepstral Coefficient based Neural Network Classifier
Authors:
- 1 February 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
The estimation of the power spectrum of discrete-time signals is one of the most fundamental and useful tools in signal processing. However, there are practical situations where one needs to look beyond the power spectrum, especially to extract information regarding the phase relations and deviations from Gaussianity. This has created considerable interest in the use of higher order spectra such as bispectrum, for the analysis of signals, particularly in the presence of additive Gaussian noise. This paper examines the use of Gammatone Cepstral Coefficients computed from the spectrum reconstructed from the bispectrum of the signal as a feature set for underwater target classification. A prototype Neural Network classifier with back propagation algorithm has been trained with the proposed feature set and the performance has been evaluated, which has yielded acceptable classification results.Keywords
This publication has 10 references indexed in Scilit:
- Gammatone Cepstral Coefficients: Biologically Inspired Features for Non-Speech Audio ClassificationIEEE Transactions on Multimedia, 2012
- CASA-Based Robust Speaker IdentificationIEEE Transactions on Audio, Speech, and Language Processing, 2012
- Application of higher order statistics/spectra in biomedical signals—A reviewMedical Engineering & Physics, 2010
- Gammatone Features and Feature Combination for Large Vocabulary Speech Recognition2007
- Application of the mutual information criterion for feature selection in computer‐aided diagnosisMedical Physics, 2001
- Evolving artificial neural networksProceedings of the IEEE, 1999
- Complex Sounds and Auditory Images1992
- Detecting a transient signal by bispectral analysisIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
- Bispectral reconstruction of signals in noise: amplitude reconstruction issuesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990
- Bispectrum estimation: A digital signal processing frameworkProceedings of the IEEE, 1987