Onset based audio segmentation for the Irish tin whistle

A technique for segmenting tin whistle audio signals according to the position of the note onsets is presented. This method focuses on the characteristics of the tin whistle within Irish traditional music, customising a time-frequency based representation for detecting the instant when a note starts and releases. Musical ornamentation, such as cuts and strikes, are very common in Irish traditional music and are played during the onset stage. Taking advantage of this musical feature, a novel technique for improving the onset time estimation is also presented.