Sound Scene Synthesis at the DCASE 2024 Challenge

TL;DR

This paper introduces a standardized evaluation framework for sound scene synthesis systems, assesses four submissions using objective and subjective metrics, and provides insights into current capabilities and future directions in the field.

Contribution

It presents a new evaluation framework for sound scene synthesis and benchmarks current systems within the DCASE 2024 Challenge.

Findings

Significant differences in system performance revealed by FAD and perceptual ratings.

Current systems show promising realism but have limitations in diversity.

The framework enables consistent comparison of sound scene synthesis methods.

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 Fr\'echet 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.