Acoustic sources are often occluded by other sounds, yet the strategie
s for recovering individual sources employed by the auditory system in
tasks such as speech recognition are remarkably robust against these
intrusions. There are often sufficient cues which allow the auditory s
ystem to determine whether sound components continue through such occl
usions. This paper reviews the situations where an assumption of conti
nuity is warranted and demonstrates how the principles governing the s
o-called ''continuity illusion'' can be used within a computational sy
stem for segregating acoustic sources.