Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks
×
Cite This
Citation & Abstract
M. Comunità, H. Phan, and JO. D.. Reiss, "Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks," Paper 10583, (2022 May.). doi:
M. Comunità, H. Phan, and JO. D.. Reiss, "Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks," Paper 10583, (2022 May.). doi:
Abstract: 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.
@article{comunità2022neural,
author={comunità, marco and phan, huy and reiss, joshua d.},
journal={journal of the audio engineering society},
title={neural synthesis of footsteps sound effects with generative adversarial networks},
year={2022},
volume={},
number={},
pages={},
doi={},
month={may},}
@article{comunità2022neural,
author={comunità, marco and phan, huy and reiss, joshua d.},
journal={journal of the audio engineering society},
title={neural synthesis of footsteps sound effects with generative adversarial networks},
year={2022},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={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.},}
TY - paper
TI - Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks
SP -
EP -
AU - Comunità, Marco
AU - Phan, Huy
AU - Reiss, Joshua D.
PY - 2022
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2022
TY - paper
TI - Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks
SP -
EP -
AU - Comunità, Marco
AU - Phan, Huy
AU - Reiss, Joshua D.
PY - 2022
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2022
AB - 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.
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.
Open Access
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, 2022Import into BibTeX
Subject:
Audio Synthesis & Audio Effects
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=21696