"Copy and scale" method for doing time-localized M.I.R. estimation:

Geoffroy Peeters
2010 Proceedings of 3rd international workshop on Machine learning and music - MML '10  
In this work we propose a "copy and scale" method based on a Nearest Neighbor paradigm to estimate time-localized parameters and apply it to the problem of beat-tracking. The Nearest Neighbor algorithm consists in assigning the information of the closest item of a pre-annotated database to an unknown target. It can be viewed as a "copy and paste" method. The "copy and scale" method we propose consists in "scaling" this information to adapt it to the properties of the unknown target. In order to
more » ... represent time-location, we represent the content of an audio signal using a sampled and tempo-normalized complex DFT of its onsetenergy-function. This representation is used as the code over which the Nearest Neighbor search is performed. Along each code of the Nearest Neighbor space, we store the corresponding annotated beatmarker positions in a normalized form. A search is then performed for a set of tempo assumptions. Once the closest code and best tempo assumption are found, the normalized beat-markers of the closest item are scaled to this tempo in order to provide the estimation of the beat-markers of the unknown item. We perform a preliminary evaluation of this method and show that, with such a simple method, we can achieve results comparable to the ones obtained with sophisticated approaches.
doi:10.1145/1878003.1878005 fatcat:by75lbvuwjeg3jixbbmuc3du7i