Performance and energy balance: a comprehensive study of state-of-the-art sound event detection systems

TL;DR

This paper analyzes the evolution of sound event detection systems over two years, focusing on their performance and energy efficiency, highlighting trends and environmental impacts of recent deep learning approaches.

Contribution

It provides a comprehensive comparison and analysis of state-of-the-art SED systems based on challenge submissions, emphasizing energy consumption and efficiency trends.

Findings

SED systems are becoming more complex and energy-intensive.

Recent systems show a trend towards improved accuracy but increased energy use.

Analysis highlights the need for energy-efficient design in SED research.

Abstract

In recent years, deep learning systems have shown a concerning trend toward increased complexity and higher energy consumption. As researchers in this domain and organizers of one of the Detection and Classification of Acoustic Scenes and Events challenges tasks, we recognize the importance of addressing the environmental impact of data-driven SED systems. In this paper, we propose an analysis focused on SED systems based on the challenge submissions. This includes a comparison across the past two years and a detailed analysis of this year's SED systems. Through this research, we aim to explore how the SED systems are evolving every year in relation to their energy efficiency implications.