Work

Energy Consumption Trends in Sound Event Detection Systems

Year: 2025

Type: conference-paper

Abstract: Deep learning systems have become increasingly energy-and computation-intensive, raising concerns about their environmental impact. As organizers of the Detection and Classification of Acoustic Scenes and Events (DCASE) challenge, we recognize the importance of addressing this issue. For the past three years, we have integrated energy consumption metrics into the evaluation of sound event detection (SED) systems. In this paper, we analyze the impact of this energy criterion on the challenge results and explore the evolution of system complexity and energy consumption over the years. We highlight a shift towards more energy-efficient approaches during training without compromising performance, while the number of operations and the system complexity continue to grow. Through this analysis, we hope to promote more environmentally friendly practices within the SED community.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10889562

Authors: Constance Douwes, Romain Serizel

Institutions: Centre National de la Recherche Scientifique, Institut national de recherche en sciences et technologies du numérique, Laboratoire Lorrain de Recherche en Informatique et ses Applications, MULTISPEECH: La parole multimodale en interaction, Université de Lorraine

Language: English

Topic: Music and Audio Processing

Subfield: Signal Processing

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Agence Nationale de la Recherche

Award: semantiC segmentatiON oF compLexe soUnd scEnes oN edge deviCEs