From acceleration to rhythmicity: Smartphone-assessed movement predicts properties of music. Issue 2 (14th March 2020)

• Record Type: Journal Article
• Authors: Irrgang, Melanie; Steffens, Jochen; Egermann, Hauke
• Is Part Of: Journal of new music research. Volume 49:Issue 2(2020)
• Page Start: 178
• Page End: 191
• Publication Date: 2020-03-14
• Subjects: Movement and computing -- music information retrieval -- embodied music cognition -- accelerometer -- mobile devices; Music -- Periodicals; Musicology -- Periodicals; 780.72
• DOI: 10.1080/09298215.2020.1715447
• Languages: English
• ISSNs: 0929-8215

Abstract

ABSTRACT: Querying music is still a disembodied process in Music Information Retrieval. Thus, the goal of the presented study was to explore how free and spontaneous movement captured by smartphone accelerometer data can be related to musical properties. Motion features related to tempo, smoothness, size, and regularity were extracted and shown to predict the musical qualities 'rhythmicity' ( R ² = .45), 'pitch level + range' ( R ² = .06) and 'complexity ( R ² = .15). We conclude that (rhythmic) music properties can be predicted from movement, and that an embodied approach to MIR is feasible.