Computational Analysis of Musical Influence: A Musicological Case Study Using MIR Tools

Collins, Nick (2010) Computational Analysis of Musical Influence: A Musicological Case Study Using MIR Tools. In: International Conference on Music Information Retrieval (ISMIR), Utrecht, The Netherlands.

Full text not available from this repository.

Abstract

Are there new insights through computational methods to the thorny problem of plotting the flow of musical influence? This project, motivated by a musicological study of early synth pop, applies MIR tools as an aid to the investigator. Web scraping and web services provide one angle, sourcing data from allmusic.com, and utilising python APIs for last.fm, EchoNest, and MusicBrainz. Charts of influence are constructed in GraphViz combining artist similarity and dates. Content based music similarity is the second approach, based around a core collection of synth pop albums. The prospect for new musical analyses are discussed with respect to these techniques.

Item Type: Conference or Workshop Item (Paper)
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Nick Collins
Date Deposited: 06 Feb 2012 20:55
Last Modified: 13 Jun 2012 14:52
URI: http://sro.sussex.ac.uk/id/eprint/28726
📧 Request an update