Dissertation/Thesis Abstract

Real time vibraphone pitch and timbre classification
by Larke, Kevin, M.A., University of California, San Diego, 2008, 51; 1459923
Abstract (Summary)

This paper examines the problem of classifying vibraphone notes in real-time based only on information from the instrument's acoustic signal. A system consisting of two basic parts is proposed: an attack identification unit for classifying the attack transients of new notes and a tone follower for tracking the overtones of sustaining notes. Both systems use a k-Nearest-Neighbor algorithm to match the unknown signal to prototype feature vectors. Several alternate feature representations are discussed including magnitude spectra and frequency domain peak information. Finally an informal evaluation of the proposed system is examined.

Indexing (document details)
Advisor: Puckette, Miller, Dubnov, Shlomo
Commitee:
School: University of California, San Diego
Department: Music
School Location: United States -- California
Source: MAI 47/03M, Masters Abstracts International
Source Type: DISSERTATION
Subjects: Music
Keywords: Vibraphone
Publication Number: 1459923
ISBN: 978-0-549-90431-1
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest