Genre-Adaptive Semantic Computing and Audio-Based Modelling for Music Mood Annotation
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 417
- Type
- D - Journal article
- DOI
-
10.1109/TAFFC.2015.2462841
- Title of journal
- IEEE Transactions on Affective Computing (TAC)
- Article number
- 2
- First page
- 122
- Volume
- 7
- Issue
- 2
- ISSN
- 1949-3045
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- Year of publication
- 2016
- 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
-
6
- Research group(s)
-
-
- Citation count
- 14
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Introduced fundamentally new models of incorporating intra- and extra musical information into music emotion recognition and assessed genre as additional context in machine learning models, yielding substantial gain in predicting the psychological valence dimension. Fazekas hosted and supervised visiting student Saari widening collaboration with The Finnish Centre of Excellence in Interdisciplinary Music Research (T. Eerola). Fazekas created a dataset of 10K mood annotated tracks which enabled further research during FAST-IMPACt (programme grant EP/L019981/1) and works exhibited at Digital Shoredich 2015 (~15k visitors, 3-400 interacting) and BBC 'Sound Now and Next' 2015 attended by influential guests in broadcast and audio (https://www.bbc.co.uk/rd/events/sound2015).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -