Auditory component analysis

Abstract

Two of the principle research areas currently being evaluated for the so-called sound source separation problem are Auditory Scene Analysis and a class of statistical analysis techniques known as Independent Component Analysis. This paper presents a methodology for combining these two techniques. It suggests a framework that first separates sounds by analyzing the incoming audio for patterns and synthesizing or filtering them accordingly. It then measures features of the resulting tracks and separates the sounds statistically by matching feature sets and attempting to make the output streams statistically independent. The proposed system is found to successfully separate artificial and acoustic mixes of sounds. As expected, the amount of separation is inversely proportional to the amount of reverberation present, number of sources, and interchannel correlation.