Attending this event?
The Papers and day two Keynote schedules have not been finalized. As soon as they are, they will be posted on this page. Please check back soon for the full convention program.
Back To Schedule
Friday, October 27 • 4:30pm - 5:30pm
Can AI-based methods revamp audio coding?

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Deep learning/AI techniques have shown to be highly successful in audio signal processing, for example in denoising and audio source separation. In coding of audio signals there has been remarkably impressive performance for AI methods in coding speech at a low bit rate. Coding of general audio, such as music, has so far been a considerably harder challenge. However, recent advances in the field have resulted in AI-based systems that are competitive with traditional perceptual audio codecs.
This workshop, organized by the AES Technical Committee on Coding of Audio Signals, contains panelists from both industry and academia and will give an introduction to the topic, brief presentations of current techniques, followed by an interactive discussion between the audience and the panel about future directions and applications in this emerging field.


Minje Kim

Indiana University

Friday October 27, 2023 4:30pm - 5:30pm EDT