Sound Scene Synthesis at the DCASE 2024 Challenge
It provides a benchmark for researchers in audio synthesis, though it is incremental as it focuses on evaluation rather than new methods.
The paper introduced a standardized evaluation framework for sound scene synthesis systems at the DCASE 2024 Challenge, analyzing four submissions using Fréchet Audio Distance and human ratings to reveal current capabilities and limitations.
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.