Files in this item



application/pdfLazar481.pdf (601kB)
(no description provided)PDF


application/octet-streamLazar481.epub (1MB)
(no description provided)Unknown


Title:Who’s playing? Towards machine-assisted identification of jazz trumpeters by timbre
Author(s):Lazar, Janet G.; Lesk, Michael
Subject(s):jazz information retrieval
music information retrieval
performer identification
timbre recognition
individuality in music performance
Abstract:The goal of our proposed study is to contribute to the growing research in machine-assisted identification of jazz performers. In particular, we seek to identify unknown jazz trumpeters. We plan to take an approach that has not received recent attention; namely, using human observation to compare spectrograms and other data representing musical timbre. We believe that human observation, when combined with machine learning, will improve accuracy of timbre recognition and performer identification. We will collect 100 music samples: five each from 20 trumpeters. We will manually sort spectrograms and other data in order to distinguish the most salient timbre characteristics. Once we choose those features, we will use a computer to filter for them. If our approach is successful, we will develop a larger database of trumpet solos.
Issue Date:2016-03-15
Citation Info:NA
Series/Report:IConference 2016 Proceedings
Genre:Conference Poster
Rights Information:Copyright 2016 is held by the authors. Copyright permissions, when appropriate, must be obtained directly from the authors.
Date Available in IDEALS:2016-03-08

This item appears in the following Collection(s)

Item Statistics