Reduce Computational Complexity for Continuous Wavelet Transform in Acoustic Recognition Using Hop Size

TL;DR

This paper introduces a method to reduce the computational cost of continuous wavelet transform in acoustic recognition by applying it selectively with a hop size, maintaining performance while saving resources.

Contribution

It proposes a novel approach of applying CWT to a subset of samples based on hop size, reducing computation without sacrificing accuracy.

Findings

Significant reduction in computational costs.

Maintained robustness of acoustic recognition models.

Efficient CWT application with minimal performance loss.

Abstract

In recent years, the continuous wavelet transform (CWT) has been employed as a spectral feature extractor for acoustic recognition tasks in conjunction with machine learning and deep learning models. However, applying the CWT to each individual audio sample is computationally intensive. This paper proposes an approach that applies the CWT to a subset of samples, spaced according to a specified hop size. Experimental results demonstrate that this method significantly reduces computational costs while maintaining the robust performance of the trained models.