Sound Event Detection: A Tutorial

TL;DR

This tutorial provides an overview of sound event detection, covering its definition, signal processing, machine learning methods, evaluation techniques, and future research directions.

Contribution

It offers a comprehensive introduction to SED, integrating foundational concepts, current methodologies, and future perspectives in a single tutorial.

Findings

Overview of signal processing techniques for SED

Discussion of machine learning approaches in SED

Insights into evaluation metrics and future challenges

Abstract

The goal of automatic sound event detection (SED) methods is to recognize what is happening in an audio signal and when it is happening. In practice, the goal is to recognize at what temporal instances different sounds are active within an audio signal. This paper gives a tutorial presentation of sound event detection, including its definition, signal processing and machine learning approaches, evaluation, and future perspectives.