Nonlinear Schur-Type Audio Signal Parameterization for Convolutional Networks
- 7 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1665-1669
Abstract
This article introduces a novel signal parameterization approach, termed nonlinear Schur-type signal parameterization, designed to enhance machine learning tasks such as signal classification and recognition. Traditional linear parameterization methods often struggle with the complex, nonlinear nature of real-world data. The mathematical foundation of the proposed parameterization method is extraction of Schur coefficients. The presented method is scalable and can be adjusted to the signal nature. The nonlinear Schur parameterization produces a matrix of Schur coefficients in time, dedicated to be a 2D input of convolutional neural networks (CNN). The performed experiments for the audio signals from open access datasets show that the signal representation in the form of the Schur coefficients is very efficient for recognition performance. The results obtained by CNN show an improvement in the classification accuracy in comparison with solutions based on preprocessing in frequency domain as FFT or MFCC.Keywords
This publication has 29 references indexed in Scilit:
- AudioMNIST: Exploring Explainable Artificial Intelligence for audio analysis on a simple benchmarkJournal of the Franklin Institute, 2023
- Α Respiratory Sound Database for the Development of Automated Classification2017
- Empirical Mode Decomposition for adaptive AM-FM analysis of Speech: A ReviewSpeech Communication, 2017
- Improving the approximation ability of Volterra series identified with a cross-correlation methodNonlinear Dynamics, 2014
- Volterra-type models for nonlinear systems identificationApplied Mathematical Modelling, 2014
- Multidimensional Nonlinear Schur Parametrization of NonGaussian Stochastic Signals Part Three: Low-Complexity Staircase SolutionMultidimensional Systems and Signal Processing, 2004
- Multidimensional Nonlinear Schur Parametrization of NonGaussian Stochastic Signals, Part Two: Generalized Schur AlgorithmMultidimensional Systems and Signal Processing, 2004
- Multidimensional Nonlinear Schur Parametrization of NonGaussian Stochastic Signals. Part One: Statement of the ProblemMultidimensional Systems and Signal Processing, 2004
- The Generalized Schur Algorithm: Approximation and Hierarchy1988
- A new notation for quantum mechanicsMathematical Proceedings of the Cambridge Philosophical Society, 1939