Towards Cross-Version Harmonic Analysis of Music

• Published in: IEEE transactions on multimedia Vol. 14; no. 3; pp. 770 - 782
• Main Authors: Ewert, S., Muller, M., Konz, V., Mullensiefen, D., Wiggins, G. A.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.06.2012; Institute of Electrical and Electronics Engineers
• Subjects: Acoustics; Alignment; Applied sciences; chord recognition; Computer science; control theory; systems; Educational institutions; Exact sciences and technology; Fundamental areas of phenomenology (including applications); Harmonic analysis; Information systems. Data bases; Labeling; Memory organisation. Data processing; Music; Music and musical intruments; music information retrieval; music synchronization; Physics; Reliability; Software; Synchronization; Sound recording; Sound reproduction; Harmonic analysis; Information retrieval; Symbolic computation; Synchronization; Task analysis; Annotation; chord recognition; Alignment; Music; Musical acoustics; Audio acoustics; music synchronization; Version management; Quantitative analysis; Sound record; music information retrieval
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2012.2190047

For a given piece of music, there often exist multiple versions belonging to the symbolic (e.g., MIDI representations), acoustic (audio recordings), or visual (sheet music) domain. Each type of information allows for applying specialized, domain-specific approaches to music analysis tasks. In this paper, we formulate the idea of a cross-version analysis for comparing and/or combining analysis results from different representations. As an example, we realize this idea in the context of harmonic analysis to automatically evaluate MIDI-based chord labeling procedures using annotations given for corresponding audio recordings. To this end, one needs reliable synchronization procedures that automatically establish the musical relationship between the multiple versions of a given piece. This becomes a hard problem when there are significant local deviations in these versions. We introduce a novel late-fusion approach that combines different alignment procedures in order to identify reliable parts in synchronization results. Then, the cross-version comparison of the various chord labeling results is performed only on the basis of the reliable parts. Finally, we show how inconsistencies in these results across the different versions allow for a quantitative and qualitative evaluation, which not only indicates limitations of the employed chord labeling strategies but also deepens the understanding of the underlying music material.