AES New York 2015
Workshop W26
Sunday, November 1, 10:30 am — 12:30 pm (Room 1A10)
W26 - Application of Semantic Audio Analysis to the Music Production Workflow
Co-chairs:György Fazekas, Queen Mary University of London - London, UK
Ryan Stables, Birmingham City University - Birmingham, UK
Panelists:
Jay LeBoeuf, Real Industry - San Francisco, CA, USA; Stanford University - San Francisco, CA, USA
Bryan Pardo, Northwestern University - Evanston, IL, USA
Abstract:
Semantic audio technologies are becoming increasingly more common at various stages in the production chain, with commercial music systems benefiting from the added value imposed by features such as music recommendation and archiving. These technologies generally involve the inference of high-level attributes from an audio signal, based on either statistical features or user-defined labels, with the aim of providing interactions with data. In the field of music production, semantic audio analysis is able to provide abstractions for complex decisions and processes, leading to more intuitive and immersive platforms for audio processing. This paves the way for a wide range of novel systems such automated mixing tools, adaptive audio effects and reduced dimensionality interfaces. In this workshop we review cutting edge semantic audio technologies, in the context of intelligent music production. We aim to provide guidance for deploying semantic audio techniques throughout the music production workflow, while discussing current limitations and future directions.
