Correlation Clustering of Bird Sounds
This work addresses the problem of clustering bird sounds for ecologists and bioacoustics researchers, but it is incremental as it adapts existing correlation clustering methods to a specific domain.
The paper tackles bird sound clustering by learning pairwise probabilities from training data and applying correlation clustering to partition test sets, achieving results comparable to classification and demonstrating effectiveness on unseen bird species and environmental noise.
Bird sound classification is the task of relating any sound recording to those species of bird that can be heard in the recording. Here, we study bird sound clustering, the task of deciding for any pair of sound recordings whether the same species of bird can be heard in both. We address this problem by first learning, from a training set, probabilities of pairs of recordings being related in this way, and then inferring a maximally probable partition of a test set by correlation clustering. We address the following questions: How accurate is this clustering, compared to a classification of the test set? How do the clusters thus inferred relate to the clusters obtained by classification? How accurate is this clustering when applied to recordings of bird species not heard during training? How effective is this clustering in separating, from bird sounds, environmental noise not heard during training?