Developing and evaluating computational models of musical style
- Submitting institution
-
The Open University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1451819
- Type
- D - Journal article
- DOI
-
10.1017/S0890060414000687
- Title of journal
- AI EDAM
- Article number
- -
- First page
- 16
- Volume
- 30
- Issue
- 01
- ISSN
- 0890-0604
- Open access status
- Out of scope for open access requirements
- Month of publication
- April
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Paper introduces a fully-replicable approach to algorithmic music generation of complete pieces in the style of a given corpus, and evaluates it empirically. The research contributed to the PhD of Collins, who went on to a postdoctoral position in the Janata Lab at the Center for Mind and Brain, UC Davis, California. Our follow-up research (Journal of Creative Music Systems, 2017) established that only 20% of participants performed significantly better than chance at distinguishing the algorithms output from J.S. Bach chorales. The approach was adapted to generate the UK’s entry in an AI version of the Eurovision Song Contest: https://yorkmix.com/a-york-song-is-representing-the-uk-in-a-new-version-of-the-eurovision-song-contest-have-a-listen/
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -