國立高雄大學圖資館 |

Language: English

Back

A method of automatic recognition of...

Nam, Unjung.

A method of automatic recognition of structural boundaries in recorded musical signals.

Record Type:	Electronic resources : Monograph/item
Title/Author:	A method of automatic recognition of structural boundaries in recorded musical signals.
Author:	Nam, Unjung.
Description:	126 p.
Notes:	Adviser: Jonathan Berger.
Notes:	Source: Dissertation Abstracts International, Volume: 65-09, Section: A, page: 3212.
Contained By:	Dissertation Abstracts International65-09A.
Subject:	Music.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3145566
ISBN:	0496045288

A method of automatic recognition of structural boundaries in recorded musical signals.
Nam, Unjung.

A method of automatic recognition of structural boundaries in recorded musical signals. - 126 p.

Adviser: Jonathan Berger.

Thesis (Ph.D.)--Stanford University, 2004.

In this thesis a methodology is proposed that attempts to derive salient and hierarchical musical structures from a raw audio signal by accessing the degree of novelty and redundancy throughout a musical signal. The work expands upon a technique of determining the degree of novelty in an audio signal by correlating the similarity matrix along the diagonal of a so-called checkerboard kernel.

ISBN: 0496045288Subjects--Topical Terms:

227185
Music.

A method of automatic recognition of structural boundaries in recorded musical signals.
LDR:03098nmm _2200301 _450 001 162833
005 20051017073528.5
008 090528s2004 eng d
020 $a 0496045288
035 $a 00149334
040 $a UnM $c UnM
100 0 $a Nam, Unjung. $3 227978
245 1 2 $a A method of automatic recognition of structural boundaries in recorded musical signals.
300 $a 126 p.
500 $a Adviser: Jonathan Berger.
500 $a Source: Dissertation Abstracts International, Volume: 65-09, Section: A, page: 3212.
502 $a Thesis (Ph.D.)--Stanford University, 2004.
520 # $a In this thesis a methodology is proposed that attempts to derive salient and hierarchical musical structures from a raw audio signal by accessing the degree of novelty and redundancy throughout a musical signal. The work expands upon a technique of determining the degree of novelty in an audio signal by correlating the similarity matrix along the diagonal of a so-called checkerboard kernel.
520 # $a Music is structured at a variety of levels ranging from the quasi-periodicity of frequency that provides the percept of pitch to macro levels of large-scale musical forms. Intermediate levels of structure include structures such as motives and phrases. These structures constitute the salient perceptual units that listeners use to comparatively assess music in terms of the degree of similarity either within a given piece or between pieces. While human listeners are facile at distinguishing recurrence and contrast in music the same task has proven elusive in machine listening paradigms.
520 # $a The research is applicable both to segmentation tasks within a recorded musical excerpt of work, and to comparative tasks amongst multiple excerpts or works. The implications of this research on machine recognition of music and music information retrieval are explored and the applications of automatic music segmentation on music summarization, is illustrated.
520 # $a This dissertation explores a method of determining appropriate analysis settings for the self-similarity method in order to determine meaningful structural segmentation of the music. Instead of arbitrarily selecting a kernel size, or pre-determining a kernel size at a level that will detect redundancy at a particular structural level, we recursively grow the kernel size in order to find multiple hierarchical musical structures within the signal. The meaningful kernel sizes are extracted by detecting the local peaks from the normalized variances of the novelty matrix. Finally, novelty scores at these kernel sizes are plotted to observe the hierarchical musical structure of the signal with regard to the novelty and the redundancy.
590 $a School code: 0212.
650 # 0 $a Music. $3 227185
650 # 0 $a Computer Science. $3 212513
690 $a 0413
690 $a 0984
710 0 # $a Stanford University. $3 212607
773 0 # $g 65-09A. $t Dissertation Abstracts International
790 $a 0212
790 1 0 $a Berger, Jonathan, $e advisor
791 $a Ph.D.
792 $a 2004
856 4 0 $u http://libsw.nuk.edu.tw:81/login?url=http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3145566 $z http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3145566