Serrà Julià, JoanKantz, HolgerAndrzejak, Ralph Gregor2021-01-292021-01-292010Serrà J, Kantz H, Andrzejak RG. Model-based cover song detection via threshold autoregressive forecasts. In: ACM Multimedia, International Workshop on Machine Learning and Music (MML); 2010 Oct 25-29; Firenze, Italy. New York: Association for Computing Machinery; 2010. p. 13-6. DOI: 10.1145/1878003.1878008http://hdl.handle.net/10230/46290Comunicació presentada a ACM Multimedia, International Workshop on Machine Learning and Music (MML), celebrat del 25 al 29 d'octubre de 2010 a Florència, Itàlia.Current systems for cover song detection are based on a model-free approach: they basically search for similarities in descriptor time series reflecting the evolution of tonal information in a musical piece. In this contribution we propose the use of a model-based approach. In particular, we explore threshold autoregressive models and the concept of cross-prediction error, i.e. a measure of to which extent a model trained on one song's descriptor time series is able to predict the covers'. Results indicate that the considered approach can provide competitive accuracies while being considerably fast and with potentially less storage requirements. Furthermore, the approach is parameter-free from the user's perspective, what provides a robust and straightforward application of it.application/pdfeng© ACM, 2010. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Multimedia, International Workshop on Machine Learning and Music (MML), (2011) http://doi.acm.org/10.1145/1878003.1878008info:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1145/1878003.1878008MusicInformation retrievalThreshold autoregressive modelsPredictionCover songsVersionsinfo:eu-repo/semantics/openAccess