Learning Sparse Adversarial Dictionaries For Multi-Class Audio Classification

TL;DR

This paper introduces a novel discriminative dictionary learning approach for multi-class audio classification, enhancing class-specific representation and robustness against noise, with demonstrated effectiveness in various classification tasks.

Contribution

It proposes a new method for learning class-specific adversarial dictionaries by integrating discriminative terms into the dictionary learning process.

Findings

Improved classification accuracy with learned dictionaries.

Effective in both binary and multi-class audio classification.

Demonstrates robustness to noise and overlapping audio events.

Abstract

Audio events are quite often overlapping in nature, and more prone to noise than visual signals. There has been increasing evidence for the superior performance of representations learned using sparse dictionaries for applications like audio denoising and speech enhancement. This paper concentrates on modifying the traditional reconstructive dictionary learning algorithms, by incorporating a discriminative term into the objective function in order to learn class-specific adversarial dictionaries that are good at representing samples of their own class at the same time poor at representing samples belonging to any other class. We quantitatively demonstrate the effectiveness of our learned dictionaries as a stand-alone solution for both binary as well as multi-class audio classification problems.