Effects of Added Vocals and Human Production to AI-composed Music on Listener’s Appreciation

Show simple item record

dc.contributor.author Dallas, Liam
dc.contributor.author Morreale, Fabio
dc.coverage.spatial Online
dc.date.accessioned 2021-07-07T02:49:18Z
dc.date.available 2021-07-07T02:49:18Z
dc.date.issued 2020-10-19
dc.identifier.citation Proceedings of the 2020 Joint Conference on AI Music Creativity. KTH Royal Institute of Technology, Stockholm, Sweden. 123-130. 19 Oct 2020
dc.identifier.uri https://hdl.handle.net/2292/55473
dc.description.abstract We investigated the extent to which listeners’ appreciation for AI composed music would change with the addition of vocals and human production. By combining a variety of commercially available and ad-hoc created software, we created four songs entirely composed by forms of machine intelligence. We then created 4 different conditions: with vs. without vocals (with lyrics generated by an AI), and human vs. AI production. We performed an experimental study with 40 participants and found that the added vocals did not improve listeners’ appreciation. Human-produced songs were also not better appreciated than AI-produced ones. By analyzing participants’ comments, we discuss possible reasons behind these results. Keywords: AI-music; music perception; listener appreciation; vocals
dc.relation.ispartof The 2020 Joint Conference on AI Music Creativity
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher.
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm
dc.title Effects of Added Vocals and Human Production to AI-composed Music on Listener’s Appreciation
dc.type Conference Item
dc.identifier.doi 10.30746/978-91-519-5560-5
dc.date.updated 2021-06-30T05:43:07Z
dc.rights.holder Copyright: The author en
pubs.author-url https://boblsturm.github.io/aimusic2020/programme.html#papers
pubs.finish-date 2020-10-23
pubs.start-date 2020-10-19
dc.rights.accessrights http://purl.org/eprint/accessRights/OpenAccess en
pubs.subtype Proceedings
pubs.elements-id 857743


Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record

Share

Search ResearchSpace


Browse

Statistics