Multimed Tools Appl (2013) 65:467–494
DOI 10.1007/s11042-012-1042-z
Adaptive music retrieval – a state of the art
Sebastian Stober · Andreas Nürnberger
Published online: 6 March 2012
© Springer Science+Business Media, LLC 2012
Abstract With the development of more and more sophisticated Music Information
Retrieval approaches, aspects of adaptivity are becoming an increasingly important
research topic. Even though, adaptive techniques have already found their way
into Music Information Retrieval systems and contribute to robustness or user
satisfaction they are not always identified as such. This paper attempts a structured
view on the last decade of Music Information Retrieval research from the perspective
of adaptivity in order to increase awareness and promote the application and further
development of adaptive techniques. To this end, different approaches from a wide
range of application areas that share the common aspect of adaptivity are identified
and systematically categorized.
Keywords Music information retrieval · Adaptive systems · Survey · Overview
1 Introduction
Why is adaptivity interesting in the context of Music Information Retrieval (MIR)?
Even though the term “adaptive” does not appear directly in recent surveys by
Orio [69] and Casey et al. [14] nor in the analysis of the “ISMIR cloud” by Grachten
et al. [27], adaptivity is a core element of many Music Information Retrieval
applications. Whilst not (yet) being a primary research topic in Music Information
Retrieval, studying adaptivity has a long tradition in the field of control theory
[1, 58], artificial neural networks and nature-inspired systems in general [25, 53].
In classic (text) information retrieval the term “adaptive information retrieval” was
coined in the late eighties by Belew [6] and with “adaptive hypermedia” a whole
S. Stober (B ) · A. Nürnberger
Data & Knowledge Engineering Group, Faculty of Computer Science,
Otto-von-Guericke-University Magdeburg,
Universitätsplatz 2, 39106 Magdeburg, Germany
e-mail: stober@ovgu.de