Taiwanese computer scientists have developed a neural network program that can classify music on its beat and tempo. They hope that the new system could be boon for music archivists with large numbers of untagged recordings and for users searching through mislabeled MP3 libraries.
The team has so far tested their approach on a collection of several hundred ballroom dance music files. Lead researchers Mao-Yuan Kao and Chang-Biau Yang of National Sun Yat-sen University, in Kaohsiung and Shyue-Horng Shiau of the Chang Jung Christian University hope to combine the strengths of two main approaches to classifying music — the eponymous Ellis and Dixon methods — and to use a neural network to do the initial classification.
The researchers' paper on the method was published in the International Journal of Intelligent Information and Database Systems, Vol. 3, No. 3, 2009.
View Full Article