Energy distribution for Coefficients of Redundant Signal Representations of Music

Line Ørtoft Endelt, Anders la Cour-Harbo

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

In this paper we investigate how the energy is distributed in the coefficients vector of various redundant signal representations of music signals. The representations are found using Basis Pursuit, Matching Pursuit, Alternating Projections, Best Orthogonal Basis and Method of Frames, with five different time-frequency dictionaries. We have applied these methods to music to examine their ability to express music signals in a sparse manner for a number of dictionaries and window lengths. The evaluation is based on the m-term approximation needed to represent 90 %, 95 %, 99 % and 99.9 % of the energy in the coefficients, also the time consummation for finding the representations are considered. The distribution of energy in the coefficients of the representations found using Basis Pursuit, Matching Pursuit, Alternating Projections and Best Orthogonal Basis depends mainly on the signal, and less on the minimization method, the dictionary and the length of the analysis window. The results indicate, that the sparseness of the representations do indeed tell something about the music signal, and this is an interesting subject for further investigation.
Original languageEnglish
Title of host publicationProceedings of SPARS05
Publication date2005
Publication statusPublished - 2005
EventSPARS05 Workshop - Rennes, France
Duration: 16 Nov 200518 Nov 2005

Conference

ConferenceSPARS05 Workshop
CountryFrance
CityRennes
Period16/11/200518/11/2005

Fingerprint

Glossaries

Keywords

  • Redundant Signal Representation
  • Music Signals
  • Computation Time

Cite this

@inproceedings{f41088e09c2c11db8ed6000ea68e967b,
title = "Energy distribution for Coefficients of Redundant Signal Representations of Music",
abstract = "In this paper we investigate how the energy is distributed in the coefficients vector of various redundant signal representations of music signals. The representations are found using Basis Pursuit, Matching Pursuit, Alternating Projections, Best Orthogonal Basis and Method of Frames, with five different time-frequency dictionaries. We have applied these methods to music to examine their ability to express music signals in a sparse manner for a number of dictionaries and window lengths. The evaluation is based on the m-term approximation needed to represent 90 {\%}, 95 {\%}, 99 {\%} and 99.9 {\%} of the energy in the coefficients, also the time consummation for finding the representations are considered. The distribution of energy in the coefficients of the representations found using Basis Pursuit, Matching Pursuit, Alternating Projections and Best Orthogonal Basis depends mainly on the signal, and less on the minimization method, the dictionary and the length of the analysis window. The results indicate, that the sparseness of the representations do indeed tell something about the music signal, and this is an interesting subject for further investigation.",
keywords = "Redundant Signal Representation, Music Signals, Computation Time",
author = "Endelt, {Line {\O}rtoft} and {la Cour-Harbo}, Anders",
year = "2005",
language = "English",
booktitle = "Proceedings of SPARS05",

}

Endelt, LØ & la Cour-Harbo, A 2005, Energy distribution for Coefficients of Redundant Signal Representations of Music. in Proceedings of SPARS05. SPARS05 Workshop, Rennes, France, 16/11/2005.

Energy distribution for Coefficients of Redundant Signal Representations of Music. / Endelt, Line Ørtoft; la Cour-Harbo, Anders.

Proceedings of SPARS05. 2005.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Energy distribution for Coefficients of Redundant Signal Representations of Music

AU - Endelt, Line Ørtoft

AU - la Cour-Harbo, Anders

PY - 2005

Y1 - 2005

N2 - In this paper we investigate how the energy is distributed in the coefficients vector of various redundant signal representations of music signals. The representations are found using Basis Pursuit, Matching Pursuit, Alternating Projections, Best Orthogonal Basis and Method of Frames, with five different time-frequency dictionaries. We have applied these methods to music to examine their ability to express music signals in a sparse manner for a number of dictionaries and window lengths. The evaluation is based on the m-term approximation needed to represent 90 %, 95 %, 99 % and 99.9 % of the energy in the coefficients, also the time consummation for finding the representations are considered. The distribution of energy in the coefficients of the representations found using Basis Pursuit, Matching Pursuit, Alternating Projections and Best Orthogonal Basis depends mainly on the signal, and less on the minimization method, the dictionary and the length of the analysis window. The results indicate, that the sparseness of the representations do indeed tell something about the music signal, and this is an interesting subject for further investigation.

AB - In this paper we investigate how the energy is distributed in the coefficients vector of various redundant signal representations of music signals. The representations are found using Basis Pursuit, Matching Pursuit, Alternating Projections, Best Orthogonal Basis and Method of Frames, with five different time-frequency dictionaries. We have applied these methods to music to examine their ability to express music signals in a sparse manner for a number of dictionaries and window lengths. The evaluation is based on the m-term approximation needed to represent 90 %, 95 %, 99 % and 99.9 % of the energy in the coefficients, also the time consummation for finding the representations are considered. The distribution of energy in the coefficients of the representations found using Basis Pursuit, Matching Pursuit, Alternating Projections and Best Orthogonal Basis depends mainly on the signal, and less on the minimization method, the dictionary and the length of the analysis window. The results indicate, that the sparseness of the representations do indeed tell something about the music signal, and this is an interesting subject for further investigation.

KW - Redundant Signal Representation

KW - Music Signals

KW - Computation Time

M3 - Article in proceeding

BT - Proceedings of SPARS05

ER -