Raw Audio Classification with Cosine Convolutional Neural Network (CosCovNN)

TL;DR

The paper proposes a framework for raw audio classification using cosine-based CNNs, introducing Cosine Convolutional Neural Network (CosCovNN) that replaces standard CNN filters with cosine filters to reduce parameters by about $77\%$ while improving accuracy. It further extends to a memory-enabled, vector-quantised variant (VQCCM) that achieves state-of-the-art performance across five datasets. The findings indicate that cosine filters can markedly enhance both efficiency and accuracy in processing raw audio waveforms, enabling compact, high-performance models for audio classification. This approach has practical implications for deploying robust audio classifiers in resource-constrained environments.

Abstract

This study explores the field of audio classification from raw waveform using Convolutional Neural Networks (CNNs), a method that eliminates the need for extracting specialised features in the pre-processing step. Unlike recent trends in literature, which often focuses on designing frontends or filters for only the initial layers of CNNs, our research introduces the Cosine Convolutional Neural Network (CosCovNN) replacing the traditional CNN filters with Cosine filters. The CosCovNN surpasses the accuracy of the equivalent CNN architectures with approximately $77\%$ less parameters. Our research further progresses with the development of an augmented CosCovNN named Vector Quantised Cosine Convolutional Neural Network with Memory (VQCCM), incorporating a memory and vector quantisation layer VQCCM achieves state-of-the-art (SOTA) performance across five different datasets in comparison with existing literature. Our findings show that cosine filters can greatly improve the efficiency and accuracy of CNNs in raw audio classification.