You are currently logged in as an
Institutional Subscriber.
If you would like to logout,
please click on the button below.
Home / Publications / E-library page
Only AES members and Institutional Journal Subscribers can download
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.
Author (s): Comunità, Marco; Phan, Huy; Reiss, Joshua D.
Affiliation:
Centre for Digital Music, Queen Mary University of London, UK
(See document for exact affiliation information.)
AES Convention: 152
Paper Number:10583
Publication Date:
2022-05-06
Import into BibTeX
Session subject:
Audio Synthesis & Audio Effects
Permalink: https://aes2.org/publications/elibrary-page/?id=21696
(2755KB)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
Comunità, Marco; Phan, Huy; Reiss, Joshua D.; 2022; Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks [PDF]; Centre for Digital Music, Queen Mary University of London, UK; Paper 10583; Available from: https://aes2.org/publications/elibrary-page/?id=21696
Comunità, Marco; Phan, Huy; Reiss, Joshua D.; Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks [PDF]; Centre for Digital Music, Queen Mary University of London, UK; Paper 10583; 2022 Available: https://aes2.org/publications/elibrary-page/?id=21696