Decision time horizon for music genre classification using short time features

Peter Ahrendt; Anders Meng; Jan Larsen

Decision time horizon for music genre classification using short time features

Peter Ahrendt
, Anders Meng
, Jan Larsen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

177 Downloads (Orbit)

Abstract

In this paper music genre classification has been explored with special emphasis on the decision time horizon and ranking of tapped-delay-line short-time features. Late information fusion as e.g. majority voting is compared with techniques of early information fusion such as dynamic PCA (DPCA). The most frequently suggested features in the literature were employed including mel-frequency cepstral coefficients (MFCC), linear prediction coefficients (LPC), zero-crossing rate (ZCR), and MPEG-7 features. To rank the importance of the short time features consensus sensitivity analysis is applied. A Gaussian classifier (GC) with full covariance structure and a linear neural network (NN) classifier are used.

Original language	English
Title of host publication	Proceedings of the 12th European Signal Processing Conference
Publication date	2004
Pages	1293-1296
Publication status	Published - 2004
Event	XII. European Signal Processing Conference - Vienna, Austria Duration: 6 Sept 2004 → 10 Sept 2004 Conference number: 12

Conference

Conference	XII. European Signal Processing Conference
Number	12
Country/Territory	Austria
City	Vienna
Period	06/09/2004 → 10/09/2004

Access to Document

Fulltext

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{63b4a84ba9ec4b7f85985cd6caad60ad,

title = "Decision time horizon for music genre classification using short time features",

abstract = "In this paper music genre classification has been explored with special emphasis on the decision time horizon and ranking of tapped-delay-line short-time features. Late information fusion as e.g. majority voting is compared with techniques of early information fusion such as dynamic PCA (DPCA). The most frequently suggested features in the literature were employed including mel-frequency cepstral coefficients (MFCC), linear prediction coefficients (LPC), zero-crossing rate (ZCR), and MPEG-7 features. To rank the importance of the short time features consensus sensitivity analysis is applied. A Gaussian classifier (GC) with full covariance structure and a linear neural network (NN) classifier are used.",

keywords = "decision time horizon, feature ranking, music genre classification, majority voting, dynamic PCA",

author = "Peter Ahrendt and Anders Meng and Jan Larsen",

year = "2004",

language = "English",

pages = "1293--1296",

booktitle = "Proceedings of the 12th European Signal Processing Conference",

note = "XII. European Signal Processing Conference, EUSIPCO 2004 ; Conference date: 06-09-2004 Through 10-09-2004",

}

TY - GEN

T1 - Decision time horizon for music genre classification using short time features

AU - Ahrendt, Peter

AU - Meng, Anders

AU - Larsen, Jan

N1 - Conference code: 12

PY - 2004

Y1 - 2004

N2 - In this paper music genre classification has been explored with special emphasis on the decision time horizon and ranking of tapped-delay-line short-time features. Late information fusion as e.g. majority voting is compared with techniques of early information fusion such as dynamic PCA (DPCA). The most frequently suggested features in the literature were employed including mel-frequency cepstral coefficients (MFCC), linear prediction coefficients (LPC), zero-crossing rate (ZCR), and MPEG-7 features. To rank the importance of the short time features consensus sensitivity analysis is applied. A Gaussian classifier (GC) with full covariance structure and a linear neural network (NN) classifier are used.

AB - In this paper music genre classification has been explored with special emphasis on the decision time horizon and ranking of tapped-delay-line short-time features. Late information fusion as e.g. majority voting is compared with techniques of early information fusion such as dynamic PCA (DPCA). The most frequently suggested features in the literature were employed including mel-frequency cepstral coefficients (MFCC), linear prediction coefficients (LPC), zero-crossing rate (ZCR), and MPEG-7 features. To rank the importance of the short time features consensus sensitivity analysis is applied. A Gaussian classifier (GC) with full covariance structure and a linear neural network (NN) classifier are used.

KW - decision time horizon

KW - feature ranking

KW - music genre classification

KW - majority voting

KW - dynamic PCA

M3 - Article in proceedings

SP - 1293

EP - 1296

BT - Proceedings of the 12th European Signal Processing Conference

T2 - XII. European Signal Processing Conference

Y2 - 6 September 2004 through 10 September 2004

ER -

Decision time horizon for music genre classification using short time features

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this