Acoustic Event Detection with Classifier Chains

TL;DR

This paper introduces a novel acoustic event detection method using classifier chains based on the probabilistic chain rule, which models event interdependence and outperforms traditional methods.

Contribution

It proposes a new AED approach with classifier chains that explicitly models interdependent events, improving detection accuracy over conventional independent classifiers.

Findings

Achieved 14.80% improvement over baseline CNN system.

Effectively models interdependence among acoustic events.

Demonstrated superior performance on real-recording datasets.

Abstract

This paper proposes acoustic event detection (AED) with classifier chains, a new classifier based on the probabilistic chain rule. The proposed AED with classifier chains consists of a gated recurrent unit and performs iterative binary detection of each event one by one. In each iteration, the event's activity is estimated and used to condition the next output based on the probabilistic chain rule to form classifier chains. Therefore, the proposed method can handle the interdependence among events upon classification, while the conventional AED methods with multiple binary classifiers with a linear layer and sigmoid function have placed an assumption of conditional independence. In the experiments with a real-recording dataset, the proposed method demonstrates its superior AED performance to a relative 14.80% improvement compared to a convolutional recurrent neural network baseline system with the multiple binary classifiers.