Scribd
Upload
42 views1 page

Automatic Music Timbre Indexing

Automatic Music Timbre Indexing

Uploaded by

Srinivas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
42 views1 page

Automatic Music Timbre Indexing

Automatic Music Timbre Indexing

Uploaded by

Srinivas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

128 Section: Music

Automatic Music Timbre Indexing


Xin Zhang
University of North Carolina at Charlotte, USA

Zbigniew W. Ras
University of North Carolina, Charlotte, USA

INTRODUCTION will formally express subjective and informal sound


characteristics. It is especially important in the light
Music information indexing based on timbre helps us- of human perception of sound timbre. Time-variant
ers to get relevant musical data in large digital music information is necessary for correct classification of
databases. Timbre is a quality of sound that distinguishes musical instrument sounds because quasi-steady state,
one music instrument from another among a wide va- where the sound vibration is stable, is not sufficient for
riety of instrument families and individual categories. human experts. Therefore, evolution of sound features
The real use of timbre-based grouping of music is very in time should be reflected in sound description as well.
nicely discussed in (Bregman, 1990). The discovered temporal patterns may better express
Typically, an uncompressed digital music record- sound features than static features, especially that classic
ing, in form of a binary file, contains a header and a features can be very similar for sounds representing the
body. A header stores file information such as length, same family or pitch, whereas changeability of features
number of channels, rate of sample frequency, etc. Un- with pitch for the same instrument makes sounds of
less being manually labeled, a digital audio recording one instrument dissimilar. Therefore, classical sound
has no description on timbre, pitch or other perceptual features can make correct identification of musical
properties. Also, it is a highly nontrivial task to label instruments independently on the pitch very difficult
those perceptual properties for every piece of music and erroneous.
object based on its data content. Lots of researchers have
explored numerous computational methods to identify
the timbre property of a sound. However, the body of a BACKGROUND
digital audio recording contains an enormous amount
of integers in a time-order sequence. For example, at a Automatic content extraction is clearly needed and
sample frequency rate of 44,100Hz, a digital recording it relates to the ability of identifying the segments of
has 44,100 integers per second, which means, in a one- audio in which particular predominant instruments were
minute long digital recording, the total number of the playing. Instruments having rich timbre are known to
integers in the time-order sequence will be 2,646,000, produce overtones, which result in a sound with a group
which makes it a very big data item. Being not in form of frequencies in clear mathematical relationships (so-
of a record, this type of data is not suitable for most called harmonics). Most western instruments produce
traditional data mining algorithms. harmonic sounds. Generally, identification of musical
Recently, numerous features have been explored to information can be performed for audio samples taken
represent the properties of a digital musical object based from real recordings, representing waveform, and for
on acoustical expertise. However, timbre description is MIDI (Musical Instrument Digital Interface) data.
basically subjective and vague, and only some subjec- MIDI files give access to highly structured data. So,
tive features have well defined objective counterparts, research on MIDI data may basically concentrate on
like brightness, calculated as gravity center of the higher level of musical structure, like key or metrical
spectrum. Explicit formulation of rules of objective information. Identifying the predominant instruments,
specification of timbre in terms of digital descriptors which are playing in the multimedia segments, is

Copyright © 2009, IGI Global, distributing in print or electronic forms without written permission of IGI Global is prohibited.

You might also like