Live Repurposing of Sounds: MIR Explorations with Personal and Crowdsourced Databases Anna Xambó Centre for Digital Music Queen Mary University of London, UK a.xambo@qmul.ac.uk Gerard Roma CeReNeM University of Huddersfield, UK g.roma@hud.ac.uk Alexander Lerch Center for Music Technology Georgia Institute of Technology, USA alexander.lerch@gatech.edu Mathieu Barthet Centre for Digital Music Queen Mary University of London, UK m.barthet@qmul.ac.uk György Fazekas Centre for Digital Music Queen Mary University of London, UK g.fazekas@qmul.ac.uk ABSTRACT The recent increase in the accessibility and size of personal and crowdsourced digital sound collections brought about a valuable resource for music creation. Finding and retrieving relevant sounds in performance leads to challenges that can be approached using music information retrieval (MIR). In this paper, we explore the use of MIR to retrieve and repurpose sounds in musical live coding. We present a live coding system built on SuperCollider enabling the use of audio content from online Creative Commons (CC) sound databases such as Freesound or personal sound databases. The novelty of our approach lies in exploiting high-level MIR methods (e.g., query by pitch or rhythmic cues) using live coding techniques applied to sounds. We demonstrate its potential through the reflection of an illustrative case study and the feedback from four expert users. The users tried the system with either a personal database or a crowdsourced database and reported its potential in facilitating tailorability of the tool to their own creative workflows. Author Keywords live coding, MIR, sound samples, Creative Commons CCS Concepts •Information systems → Music retrieval; •Applied computing → Sound and music computing; Performing arts; 1. INTRODUCTION The continuous increase of digital storage capacity, cloud computing and the social web are some of the factors that have facilitated an expansion of digital media collections, for either private use, shared use with an online community, or both. The development of Creative Commons (CC) licenses helped with creating a legal environment promoting Licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Copyright remains with the author(s). NIME’18, June 3-6, 2018, Blacksburg, Virginia, USA. audio text MIRLC API MIR CLIENT LC LANGUAGE FEATURE DATABASE SOUND DATABASE LIVE CODER INPUT SPEAKERS LC ENVIRONMENT MIRLC API: high-level live-coding access to content-based querying. MIR Client: search and retrieve audio with content-based search capabilities. LC Language: client of the live-coding environment. Figure 1: Block diagram of audio repurposing applied to live coding. shareability and repurposing 1 of digital content. Sound and music are not an exception, and large audio online databases are available using CC licenses (e.g., ccMixter, 2 Europeana Sounds, 3 Freesound, 4 Jamendo, 5 Internet Audio Archive). 6 Such databases have become a valuable resource for practitioners and researchers because they facilitate access to large collections of varied sounds, which can be incorporated into their professional workflows. However, the “findability” of sounds for particular purposes using traditional methods (e.g., query by text, directory lists, side annotations) can become a time-consuming and tedious manual labor, and automatic annotation is still not mature 1 Audio repurposing here refers to sampling and manipulating audio samples, generally from other artists, through retrieval (e.g., using queries by filter or similarity) from a database. Live audio repurposing refers to this practice in real time, suitable for performance. 2 http://ccmixter.org 3 http://www.eusounds.eu 4 http://freesound.org 5 http://www.jamendo.com 6 http://archive.org/details/audio