Automatic Programming of VST Sound Synthesizers using Deep Networks and Other Techniques

Yee-King, Matthew; Fedden, Leon and d'Inverno, Mark. 2018. Automatic Programming of VST Sound Synthesizers using Deep Networks and Other Techniques. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(2), pp. 150-159. ISSN 2471-285X [Article]

[img]
Preview
Text
myk_lf_vsti_programming.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (480kB) | Preview

Abstract or Description

Programming sound synthesizers is a complex and time-consuming task. Automatic synthesizer programming in- volves finding parameters for sound synthesizers using algorith- mic methods. Sound matching is one application of automatic programming, where the aim is to find the parameters for a synthesizer that cause it to emit as close a sound as possible to a target sound. We describe and compare several sound matching techniques that can be used to automatically program the Dexed synthesizer, which is a virtual model of a Yamaha DX7. The techniques are a hill climber, a genetic algorithm and three deep neural networks that have not been applied to the problem before. We define a sound matching task based on six sets of sounds, which we derived from increasingly complex configurations of the Dexed synthesis algorithm. A bidirectional, long short-term memory network (LSTM) with highway layers performed better than any other technique and was able to match sounds closely in 25% of the test cases. This network was also able to match sounds in near real time, once trained, which provides a significant speed advantage over previously reported techniques that are based on search heuristics. We also describe our open source framework which makes it possible to repeat our study, and to adapt it to different synthesizers and algorithmic programming techniques.

Item Type:

Article

Identification Number (DOI):

https://doi.org/10.1109/TETCI.2017.2783885

Additional Information:

© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Upon publication, authors are asked to include either a link to the abstract of the published article in IEEE Xplore®, or the article’s Digital Object Identifier (DOI).

Keywords:

Computer generated music, Signal synthesis, Artificial neural networks, Genetic algorithms, Frequency modulation

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
27 November 2017Accepted
23 March 2018Published Online
April 2018Published

Item ID:

22516

Date Deposited:

05 Dec 2017 17:53

Last Modified:

21 Mar 2021 23:12

Peer Reviewed:

Yes, this version has been peer-reviewed.

URI:

https://research.gold.ac.uk/id/eprint/22516

View statistics for this item...

Edit Record Edit Record (login required)