Upsampling artifacts in neural audio synthesis | by Jordi Pons
Details
London Audio & Music AI Meetup (virtual) - 03 Dec 2020 @ 18.30 (GMT)
We would like to invite you to our inaugural Audio & Music AI Meetup.
Featuring Jordi Pons, Research Scientist at Dolby Laboratories, presenting "Upsampling artifacts in neural audio synthesis".
- Agenda:
- 18:25: Virtual doors open
- 18:30: Talk
- 19:15: Q&A
- 19:30: Networking
- 20:30: Close
- Zoom link
The zoom link will be shared to registered participants closer to the event date. Please keep an eye on your inbox! - Abstract
A number of recent advances in audio synthesis rely on neural upsamplers, which can introduce undesired artifacts. In computer vision, upsampling artifacts have been studied and are known as checkerboard artifacts (due to their characteristic visual pattern). However, their effect has been overlooked so far in audio processing. Given their importance, together with the fact that the audio literature only provides sparse and unorganized insights, our recent work is aimed at advancing and consolidating our current understanding of neural upsamplers for audio synthesis. - Paper
https://arxiv.org/abs/2010.14356 - Bio
Jordi Pons is a researcher at Dolby Laboratories. Previously, he received a PhD in music technology, large-scale audio collections, and deep learning at the Music Technology Group (Universitat Pompeu Fabra, Barcelona). He also received an MSc in sound and music computing (Universitat Pompeu Fabra, Barcelona), and his BSc was in telecommunications engineering (Universitat Politècnica de Catalunya, Barcelona). He also interned at IRCAM (Paris), at the German Hearing Center (Hannover), at Pandora Radio (USA, Bay Area), and at Telefónica Research (Barcelona).
http://www.jordipons.me/ - Host
Kobalt Music. https://www.kobaltmusic.com/ - Sponsors
IEEE Signal Processing Society. http://www.signalprocessingsociety.org/