Audio Developer Conference

Deep learning technology is already all around us, from ubiquitous image classification, facial recognition, and of course, animoji. These techniques have already improved the state of the art in some areas of audio processing, including source separation and voice synthesis. How can we, as audio application developers, take advantage of these new opportunities? 

The goal of this talk is to provide a practical perspective on the design and implementation of deep learning techniques for audio software. We'll start with a very brief and high-level overview about what deep learning is, and then survey some of the application areas created by the technology. We'll keep the discussion grounded on specific case studies rather than abstractions. 

Attendees should leave with a better understanding of what it would take, practically, to integrate modern deep learning techniques into their audio software products.