For creating artificial room impressions, numerous reverb plugins exist and are often controllable by many parameters. To efficiently create a desired room impression, the sound engineer must be familiar with all the available reverb setting possibilities. Although plugins are usually equipped with many factory presets for exploring available reverb options, it is a time-consuming learning process to find the ideal reverb settings to create the desired room impression, especially if various reverberation plugins are available. For creating a desired room impression based on a reference audio sample, we present a method to automatically determine the best matching reverb preset across different reverb plugins. Our method uses a supervised machine-learning approach and can dramatically reduce the time spent on the reverb selection process.

Authors: Peters, Nils; Choi, Jaeyoung; Lei, Howard
Affiliations: International Computer Science Institute, Berkeley, CA, USA; University of California Berkeley, Berkeley, CA, USA(See document for exact affiliation information.)
AES Convention: 133 (October 2012) Paper Number: 8700
Publication Date: October 25, 2012 Import into BibTeX
Subject: Audio Effects and Physical Modeling
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=16443

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD 133Papers)   /conv/133/8700.pdf

Start a discussion about this paper!