W.B. de Haas

Comparing approaches to the similarity of musical chord sequences

We present a comparison between two recent approaches to the harmonic similarity of musical chords sequences. In contrast to earlier work that mainly focuses on the similarity of musical notation or musical audio, in this paper we specifically use on the symbolic chord description as the primary musical representation. For an experiment, a large chord sequence corpus was created. In this experiment we compare a geometrical and an alignment approach to harmonic similarity, and measure the effects of chord description detail and a priori key information on retrieval performance. The results show that an alignment approach significantly outperforms a geometrical approach in most cases, but that the geometrical approach is computationally more efficient than the alignment approach. Furthermore, the results demonstrate that a priori key information boosts retrieval performance, and that using a triadic chord representation yields significantly better results than a simpler or more complex chord representation.

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.

Chord Label Personalization through Deep Learning of Integrated Harmonic Interval-based Representations

Proceedings of the First International Workshop on Deep Learning and Music, joint with IJCNN, Anchorage, US, May 17-18, 2017