An auditory model for the detection of perceptual onsets and beat tracking in singing

We describe a biophysically motivated model of auditory sal ience and present results which show that the derived measure of salie nce can be used to successfully identify the position of perceptual on sets in a musical stimulus. We evaluate the method using a corpus of unacco mpanied freely sung stimuli. We briefly show that perceptual onsets d tected by the model are in good agreement with those identified by a comb ination of state-of-the-art algorithms and manual correction. We s how that this continuous measure of salience can be used to track and predi ct rhythmic structure on the basis of its periodicity, thus avoiding the necessity forad hocdecisions as to if, or when, an event has occurred.