Numerous techniques support finding sounds that are acoustically similar to a given one. It is hard, however, to find a sound to start the similarity search with. Inspired by systems for image search that allow drawing the shape to be found, we address quick input for audio retrieval. In our system, the user literally sketches a sound effect, placing curved strokes on a canvas. Each of these represents one sound from a collection of basic sounds. The audio feed-back is interactive, as is the continuous update of the list of retrieval results. The retrieval is based on symbol se-quences formed from MFCC data compared with the help of a neural net using an editing distance to allow small temporal changes.

Authors: Battermann, Michael; Heise, Sebastian; Loviscach, Jörn
Affiliations: Fachhochschule Bielefeld (University of Applied Sciences), Bielefeld, Germany; Hochschule Bremen (University of Applied Sciences), Bremen, Germany(See document for exact affiliation information.)
AES Convention: 126 (May 2009) Paper Number: 7794
Publication Date: May 1, 2009 Import into BibTeX
Subject: Sound Design and Processing
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=14990

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 126Papers)   /126/7794.pdf

Start a discussion about this paper!