Intelligent Multitrack Dynamic Range Compression
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 416
- Type
- D - Journal article
- DOI
-
10.17743/jaes.2015.0053
- Title of journal
- Journal of the Audio Engineering Society
- Article number
- -
- First page
- 412
- Volume
- 63
- Issue
- 6
- ISSN
- 1549-4950
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- 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
- 12
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- We devised an intelligent system that can autonomously perform one of the most challenging tasks in audio production. Initial experiments established expert knowledge of how audio engineers apply compressors when mixing audio. Subjective evaluation of the intelligent system showed that it outperformed amateur human mixes and an alternative approach. This and related intelligent audio production tools formed the basis of spin-out company LandR, which has over 2M users of its AI audio mastering service, and valued by investors at over ?40M. The paper led to direct industry funding from Yamaha (semantic mixing, hiraku.okumura@music.yamaha.com) and BBC (personalised compressor, Andrew.Mason@bbc.co.uk).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -