Footsteps are among the most ubiquitous sound effects in multimedia applications. There is substantial research into understanding the acoustic features and developing synthesis models for footstep sound effects. In this paper, we present a first attempt at adopting neural synthesis for this task. We implemented two GAN-based architectures and compared the results with real recordings as well as six traditional sound synthesis methods. Our architectures reached realism scores as high as recorded samples, showing encouraging results for the task at hand.

Authors: Comunità, Marco; Phan, Huy; Reiss, Joshua D.
Affiliation: Centre for Digital Music, Queen Mary University of London, UK
AES Convention: 152 (May 2022) Paper Number: 10583
Publication Date: May 2, 2022 Import into BibTeX
Subject: Audio Synthesis & Audio Effects
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=21696

Download Now (2.7 MB)

This paper is Open Access which means you can download it for free.

Learn more about the AES E-Library

E-Library Location:   /conv/152/10583.pdf

Start a discussion about this paper!