Sound Scene Synthesis at the DCASE 2024 Challenge

2025/01/15 by Mathieu Lagrange, Lagrange, Mathieu, Jun‐Won Lee +13 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2501.08587

openalex publication_date 2025/01/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents Task 7 at the DCASE 2024 Challenge: sound scene synthesis. Recent advances in sound synthesis and generative models have enabled the creation of realistic and diverse audio content. We introduce a standardized evaluation framework for comparing different sound scene synthesis systems, incorporating both objective and subjective metrics. The challenge attracted four submissions, which are evaluated using the Fréchet Audio Distance (FAD) and human perceptual ratings. Our analysis reveals significant insights into the current capabilities and limitations of sound scene synthesis systems, while also highlighting areas for future improvement in this rapidly evolving field.

Cited by

• Scene2Sound: Auditory-Grounded Soundscape Generation for 3D Gaussian Worlds

Related

• Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation
• Foley Sound Synthesis at the DCASE 2023 Challenge
• A Proposal for Foley Sound Synthesis Challenge
• Audio-visual scene classification: analysis of DCASE 2021 Challenge submissions
• Experiments on the DCASE Challenge 2016: Acoustic Scene Classification and Sound Event Detection in Real Life Recording