Classification of Musical Metre with Autocorrelation and Discriminant Functions

The performance of autocorrelation-based metre induction was tested with two large collections of folk melodies, consisting of approximately 13,000 melodies in MIDI file format, for which the correct metres were available. The analysis included a number of melodic accents assumed to contribute to metric structure. The performance was measured by the proportion of melodies whose metre was correctly classified by Multiple Discriminant Analysis. Overall, the method predicted notated metre with an accuracy of 75 % for classification into nine categories of metre. The most frequent confusions were made within the groups of duple and triple/compound metres, whereas confusions across these groups where significantly less frequent. In addition to note onset locations and note durations, Thomassen's melodic accent was found to be an important predictor of notated metre.

• Type: Conference
• Year: 2005
• Where: ISMIR
• Authors: Petri Toiviainen, Tuomas Eerola
• Keywords: Autocorrelation-based Metre Induction, Folk Melodies, Information Retrieval, ISMIR 2005, Melodic Accent