We address the problem of classifying polyphonic musical audio signals by their Meter, as 'binary' or 'ternary'. Experiments have been conducted on a 70 instances database (20s excerpts from commercial songs without particular genre or timbre restriction). The Meter is the number of beats between regularly recurring accents (or Downbeats). Our approach aims to test the hypothesis that acoustic evidences for Downbeats can be measured on the signal; putting a special focus on their temporal recurrences. We experimented several approaches to the problem of feature selection and report some interesting results: measurements of a very small set of beat descriptors (i.e. 4) and subsequent processing (based on descriptors' autocorrelation functions) permit to reach around 95% of correct classification. Using only the temporal centroid, almost 90% of correct classification can be achieved.
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.