Sound Event Detection Based on Curriculum Learning Considering Learning Difficulty of Events

TL;DR

This paper introduces a curriculum learning approach for sound event detection that trains models from easy to difficult events, significantly improving detection accuracy over conventional methods.

Contribution

The paper proposes a novel objective function for SED that incorporates curriculum learning based on event difficulty, enhancing model performance.

Findings

F-score improved by 10.09 percentage points

Effective utilization of event difficulty in training

Significant performance gain over conventional methods

Abstract

In conventional sound event detection (SED) models, two types of events, namely, those that are present and those that do not occur in an acoustic scene, are regarded as the same type of events. The conventional SED methods cannot effectively exploit the difference between the two types of events. All time frames of sound events that do not occur in an acoustic scene are easily regarded as inactive in the scene, that is, the events are easy-to-train. The time frames of the events that are present in a scene must be classified as active in addition to inactive in the acoustic scene, that is, the events are difficult-to-train. To take advantage of the training difficulty, we apply curriculum learning into SED, where models are trained from easy- to difficult-to-train events. To utilize the curriculum learning, we propose a new objective function for SED, wherein the events are trained from easy- to difficult-to-train events. Experimental results show that the F-score of the proposed method is improved by 10.09 percentage points compared with that of the conventional binary cross entropy-based SED.