Evolutionary sound matching: A test methodology and comparative study

Mitchell, Thomas J.

Abstract

With the ever-increasing complexity of sound synthesisers, there is a growing demand for automated parameter estimation and sound space navigation techniques. Recent research in this domain has focused on the application of general-purpose evolutionary algorithms to match specific types of target sounds. However, it is difficult to establish whether success or failure of a particular match is due to the inefficiency of the optimisation engine, or the limitations of the matching synthesiser. In this paper the distinction between optimiser inefficiency and synthesiser limitations is elucidated with a contrived target test methodology that enables the performance of different optimisation techniques to be measured and compared. The methodology is applied to a Frequency Modulation synthesiser, in order to compare the performance of different Evolution Strategy-based algorithms. The algorithm producing the best results with contrived targets is then used to match a non-contrived acoustic instrument tone.

Citation

Mitchell, T. J. (2007, December). Evolutionary sound matching: A test methodology and comparative study. Paper presented at Proceedings of the Sixth International Conference on Machine Learning and Applications, Cincinnati, OH, USA

• Presentation Conference Type: Conference Paper (unpublished)
• Conference Name: Proceedings of the Sixth International Conference on Machine Learning and Applications
• Conference Location: Cincinnati, OH, USA
• Start Date: Dec 13, 2007
• End Date: Dec 15, 2007
• Publication Date: Dec 1, 2007
• Deposit Date: Jun 16, 2010
• Publicly Available Date: Feb 16, 2016
• Peer Reviewed: Not Peer Reviewed
• Keywords: evolutionary sound matching
• Public URL: https://uwe-repository.worktribe.com/output/1023385
• Publisher URL: http://www.ieee.org/index.html
• Additional Information: Additional Information : Copyright © 2007 IEEE. Reprinted from Proceedings of the Sixth International Conference on Machine Learning and Applications, Cincinnati, IEEE. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of the West of England’s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [e-mail]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.