Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks

Comunità M, Phan H, Reiss JD. Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks. In: AES Convention 152. Audio Engineering Society; 2022. Paper 10583. Available from: https://aes.org/publications/elibrary-page/?id=21696

@inproceedings{Comunita2022_21696,
  author = {Comunità, Marco and Phan, Huy and Reiss, Joshua D.},
  title = {{Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks}},
  booktitle = {AES Convention 152},
  note = {Paper 10583},
  year = {2022},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21696}
}

TY  - CPAPER
TI  - Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks
AU  - Comunità, Marco
AU  - Phan, Huy
AU  - Reiss, Joshua D.
T2  - AES Convention 152
M1  - Paper 10583
PY  - 2022
DA  - 2022/05/06
UR  - https://aes.org/publications/elibrary-page/?id=21696
PB  - Audio Engineering Society
LA  - en
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.
ER  -