Automatic Programming of VST Sound Synthesizers using Deep Networks and Other Techniques
- Submitting institution
-
Goldsmiths' College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2035
- Type
- D - Journal article
- DOI
-
10.1109/TETCI.2017.2783885
- Title of journal
- IEEE Transactions on Emerging Topics in Computational Intelligence
- Article number
- -
- First page
- 150
- Volume
- 2
- Issue
- 2
- ISSN
- 2471-285X
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2018
- URL
-
http://research.gold.ac.uk/id/eprint/22516/
- 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
-
2
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work presents a novel application of deep learning to the problem of sound synthesizer programming. Compared to previous techniques, the deep network reduces the time required to derive parameters from hours or minutes to milliseconds. The author applies a method which has been used by other authors, and which they developed during their PhD work, to compare algorithms. Solving the problem in real time is a significant advance on previous solutions. This solution has greater potential for innovation into commercial music technology products which tend to be very interactive and real-time.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -