Cross recurrence quantification for cover song identification

TitleCross recurrence quantification for cover song identification
Publication TypeJournal Article
Year of Publication2009
AuthorsSerrà, J., Serra X., & Andrzejak R. G.
Journal TitleNew Journal of Physics
Volume11
Pages093017
Journal Date09/2009
AbstractThere is growing evidence that nonlinear time series analysis techniques can be used to successfully characterize, classify, or process signals derived from real-world dynamics even though these are not necessarily deterministic and stationary. In the present study we proceed in this direction by addressing an important problem our modern society is facing, the automatic classification of digital information. In particular, we address the automatic identification of cover songs, i.e. alternative renditions of a previously recorded musical piece. For this purpose we here propose a recurrence quantification analysis measure that allows tracking potentially curved and disrupted traces in cross recurrence plots. We apply this measure to cross recurrence plots constructed from the state space representation of musical descriptor time series extracted from the raw audio signal. We show that our method identifies cover songs with a higher accuracy as compared to previously published techniques. Beyond the particular application proposed here, we discuss how our approach can be useful for the characterization of a variety of signals from different scientific disciplines. We study coupled Rössler dynamics with stochastically modulated mean frequencies as one concrete example to illustrate this point.
Published documenthttp://www.iop.org/EJ/article/1367-2630/11/9/093017/njp9_9_093017.pdf
DOI10.1088/1367-2630/11/9/093017
intranet