Recent work in Audio Source Separation and Adaptive Audio Interfaces

Assoc. Prof. Bryan Pardo combines advances in artificial intelligence,
signal processing and user interface design to build tools that empower
both music creators and music listeners. In this talk, he will describe
two such tools developed in his laboratory: REPET, a repetition-based
source separation method; and the iQ intelligent equalizer.

REPET: Repetition is a core principle in music. This is especially true
for popular songs, generally marked by a noticeable repeating musical
structure, over which the singer performs varying lyrics. On this basis,
we propose a simple method for separating music and voice, by extraction
of the repeating musical structure. Evaluation on a dataset of 1,000
song clips showed that this method can improve on the performance of an
existing music/voice separation method without optimization or complex
frameworks.

iQ: Complex interfaces for audio processing tools (e.g. equalizers) can
prevent novices from achieving their desired sound modifications. We
adapt a correlational method used widely in psychoacoustics to quickly
map from high-level language-based descriptors (such as 'warm') to
audio processing parameters. This allows automated construction of
simpler interfaces for audio processing tools. The result of this is
iQ, an intelligent equalizer plug-in that helps each user discover the
equalization settings that sound best to them.