Evaluating the Role of Repeated Patterns in Folk Song Classification and Compression

According to musicological studies on oral transmission, repeated patterns are considered important for determining musical similarity in folk songs. In this paper, we study the relevance of repeated patterns for modelling similarity and compression in a retrieval setting. Using a dataset of 360 Dutch folk songs, we compare the classification accuracy of both humanly annotated patterns and automatically retrieved patterns by means of a pattern discovery algorithm. A framework is proposed to use these patterns for compression and classification in tune families. The annotated patterns allow us to compress the songs by 60% at the expense of a 3 percentage points decrease in classification accuracy. However, none of the automatic pattern discovery algorithms is able to reach a similar combination of compression ratio and retrieval accuracy. We conclude that repeated patterns are relevant for similarity estimation and compression, but that the state of the art in automatic pattern discovery cannot compete with expert annotations in this retrieval setting.