Note: This bibliographic page is archived and will no longer be updated. For an up-to-date list of publications from the Music Technology Group see the Publications list .

Exploiting Domain Knowledge in Music Information Research

Title Exploiting Domain Knowledge in Music Information Research
Publication Type Conference Paper
Year of Publication 2013
Conference Name Stockholm Music Acoustics Conference 2013 and Sound and Music Computing Conference 2013
Authors Serra, X.
Pagination 3-6
Conference Start Date 30/07/2013
Conference Location Stockholm, Sweden

Music Information Research (MIR) is a discipline that aims to understand and model music from an information processing perspective, but the successful approaches used in MIR are going beyond the traditional data processing methodologies. Most of the great advancements have been the result of combining engineering disciplines such as audio signal processing and machine learning with non-engineering disciplines such as music perception and music theory. One of the challenges in MIR is to automatically describe music audio signals, thus to develop methodologies to extract musically useful information from audio recordings. In this paper we claim that if we want to advance in this direction we should maximize the use of musical knowledge in all the steps of our research tasks. To support this claim we overview some of the work being carried out in CompMusic, a project that aims to analyze and automatically describe the music of several non-western music traditions.

preprint/postprint document