As the World Wide Web and the Internet become the dominant form of information distribution, consideration must be given to the indexing of musical material including themes, melodies, rhythm tracks, and so forth. This paper describes the implementation of an algorithm for locating song titles from the vocal input of amateur singers. The prototype algorithm can exceed 90% accuracy for nine different singers.

Author: Kahrs, Mark
Affiliation: Rutgers University, Piscataway, NJ
AES Convention: 107 (September 1999) Paper Number: 5063
Publication Date: September 1, 1999 Import into BibTeX
Subject: Miscellaneous Audio Topics
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=8117

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 aes15)   /pp9900/pp9909/4826.pdf

Start a discussion about this paper!