DCASE-2023 foley sound generation benchmark

Emerging

1papers using it

2023first seen

The 'DCASE2023 foley sound generation benchmark' is a dataset used to evaluate the performance of audio synthesis models specifically in generating foley sounds, measuring their quality through metrics like the Fréchet audio distance (FAD) score.

🔎 Find this dataset

Papers using DCASE-2023 foley sound generation benchmark (1)

EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis2023