Jam with Jamendo: Querying a Large Music Collection by Chords from a Learner's Perspective

Abstract

Nowadays, a number of online music databases are available under Creative Commons licenses (e.g. Jamendo, ccMixter). Typically, it is possible to navigate and play their content through search interfaces based on metadata and file-wide tags. However, because this music is largely unknown, additional methods of discovery need to be explored. In this paper, we focus on a use case for music learners. We present a web app prototype that allows novice and expert musicians to discover songs in Jamendo's music collection by specifying a set of chords. Its purpose is to provide a more pleasurable practice experience by suggesting novel songs to play along with, instead of practising isolated chords or with the same song over and over again. To handle less chord-oriented songs and transcription errors that inevitably arise from the automatic chord estimation used to populate the database, query results are ranked according to a computational confidence measure. In order to assess the validity of the confidence ranked system, we conducted a small pilot user study to assess its usefulness. Drawing on those preliminary findings, we identify some design recommendations for future applications of music learning and music search engines focusing on the user experience when interacting with sound.