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.
|Advisor:||Puckette, Miller, Dubnov, Shlomo|
|School:||University of California, San Diego|
|School Location:||United States -- California|
|Source:||MAI 47/03M, Masters Abstracts International|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be