Comunicació presentada a l'ICASSP 2015, International Conference on Acoustics, Speech, and Signal Processing, que es va celebrar els dies 19 al 24 d'abril de 2015 a Brisbane, Austràlia.

We perform a comparative evaluation of methodologies for computing similarity between short-time melodic fragments of audio recordings of Indian art music. We experiment with 560 different combinations of procedures and parameter values. These include the choices made for the sampling rate of the melody representation, pitch quantization levels, normalization techniques and distance measures. The dataset used for evaluation consists of 157 and 340 annotated melodic fragments of Carnatic and Hindustani music recordings, respectively. Our results indicate that melodic fragment similarity is particularly sensitive to distance measures and normalization techniques. Sampling rates do not have a significant impact for Hindustani music, but can significantly degrade the performance for Carnatic music. Overall, the performed evaluation provides a better understanding of the processing steps and parameter settings for melodic similarity in Indian art music. Importantly, it paves the way for developing unsupervised melodic pattern discovery approaches, whose evaluation is a challenging and, many times, ill-defined task.

This work is partly supported by the European Research Council under the European Union's Seventh Framework Program, as part of the Comp-Music project (ERC grant agreement 267583). JS acknowledges 2009-SGR-1434 from Generalitat de Catalunya and ICT-2011-8-318770 from the European Commission.