Perceptual feature based music classification: A DSP perspective for a new type of application

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

External Research Organisations

  • RWTH Aachen University
  • Nokia Corporation
View graph of relations

Details

Original languageEnglish
Title of host publication2008 International Conference on Embedded Computer Systems
Subtitle of host publicationArchitectures, Modeling and Simulation
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages92-99
Number of pages8
ISBN (print)9781424419852
Publication statusPublished - 5 Nov 2008
Externally publishedYes
Event2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2008 - Samos, Greece
Duration: 21 Jul 200824 Jul 2008

Abstract

Today, more and more computational power is available not only in desktop computers but also in portable devices such as smart phones or PDAs. At the same time the availability of huge non-volatile storage capacities (flash memory etc.) suggests to maintain huge music databases even in mobile devices. Automated music classification promises to allow keeping a much better overview on huge data bases for the user. Such a classification enables the user to sort the available huge music archives according to different genres which can be either predefined or user defined. It is typically based on a set of perceptual features which are extracted from the music data. Feature extraction and subsequent music classification are very computational intensive tasks. Today, a variety of music features and possible classification algorithms optimized for various application scenarios and achieving different classification qualities are under discussion. In this paper results concerning the computational needs and the achievable classification rates on different processor architectures are presented. The inspected processors include a general purpose P IV dual core processor, heterogeneous digital signal processor architectures like a Nomadik STn8810 (featuring a smart audio accelerator, SAA) as well as an OMAP2420. In order to increase classification performance, different forms of feature selection strategies (heuristic selection, full search and Mann-Whitney-Test) are applied. Furthermore, the potential of a hardware-based acceleration for this class of application is inspected by performing a fine as well as a coarse grain instruction tree analysis. Instruction trees are identified, which could be attractively implemented as custom instructions speeding up this class of applications.

Keywords

    ASIP, Feature extraction, Music classification, Music information retrieval, Processor architecture optimization, Processor performance

ASJC Scopus subject areas

Cite this

Perceptual feature based music classification: A DSP perspective for a new type of application. / Blume, H.; Haller, M.; Botteck, M. et al.
2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation. Institute of Electrical and Electronics Engineers Inc., 2008. p. 92-99.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Blume, H, Haller, M, Botteck, M & Theimer, W 2008, Perceptual feature based music classification: A DSP perspective for a new type of application. in 2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation. Institute of Electrical and Electronics Engineers Inc., pp. 92-99, 2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2008, Samos, Greece, 21 Jul 2008. https://doi.org/10.1109/ICSAMOS.2008.4664851
Blume, H., Haller, M., Botteck, M., & Theimer, W. (2008). Perceptual feature based music classification: A DSP perspective for a new type of application. In 2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (pp. 92-99). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSAMOS.2008.4664851
Blume H, Haller M, Botteck M, Theimer W. Perceptual feature based music classification: A DSP perspective for a new type of application. In 2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation. Institute of Electrical and Electronics Engineers Inc. 2008. p. 92-99 doi: 10.1109/ICSAMOS.2008.4664851
Blume, H. ; Haller, M. ; Botteck, M. et al. / Perceptual feature based music classification : A DSP perspective for a new type of application. 2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation. Institute of Electrical and Electronics Engineers Inc., 2008. pp. 92-99
Download
@inproceedings{420508407d08444b9d69a11bb751853d,
title = "Perceptual feature based music classification: A DSP perspective for a new type of application",
abstract = "Today, more and more computational power is available not only in desktop computers but also in portable devices such as smart phones or PDAs. At the same time the availability of huge non-volatile storage capacities (flash memory etc.) suggests to maintain huge music databases even in mobile devices. Automated music classification promises to allow keeping a much better overview on huge data bases for the user. Such a classification enables the user to sort the available huge music archives according to different genres which can be either predefined or user defined. It is typically based on a set of perceptual features which are extracted from the music data. Feature extraction and subsequent music classification are very computational intensive tasks. Today, a variety of music features and possible classification algorithms optimized for various application scenarios and achieving different classification qualities are under discussion. In this paper results concerning the computational needs and the achievable classification rates on different processor architectures are presented. The inspected processors include a general purpose P IV dual core processor, heterogeneous digital signal processor architectures like a Nomadik STn8810 (featuring a smart audio accelerator, SAA) as well as an OMAP2420. In order to increase classification performance, different forms of feature selection strategies (heuristic selection, full search and Mann-Whitney-Test) are applied. Furthermore, the potential of a hardware-based acceleration for this class of application is inspected by performing a fine as well as a coarse grain instruction tree analysis. Instruction trees are identified, which could be attractively implemented as custom instructions speeding up this class of applications.",
keywords = "ASIP, Feature extraction, Music classification, Music information retrieval, Processor architecture optimization, Processor performance",
author = "H. Blume and M. Haller and M. Botteck and W. Theimer",
year = "2008",
month = nov,
day = "5",
doi = "10.1109/ICSAMOS.2008.4664851",
language = "English",
isbn = "9781424419852",
pages = "92--99",
booktitle = "2008 International Conference on Embedded Computer Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",
note = "2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2008 ; Conference date: 21-07-2008 Through 24-07-2008",

}

Download

TY - GEN

T1 - Perceptual feature based music classification

T2 - 2008 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation, IC-SAMOS 2008

AU - Blume, H.

AU - Haller, M.

AU - Botteck, M.

AU - Theimer, W.

PY - 2008/11/5

Y1 - 2008/11/5

N2 - Today, more and more computational power is available not only in desktop computers but also in portable devices such as smart phones or PDAs. At the same time the availability of huge non-volatile storage capacities (flash memory etc.) suggests to maintain huge music databases even in mobile devices. Automated music classification promises to allow keeping a much better overview on huge data bases for the user. Such a classification enables the user to sort the available huge music archives according to different genres which can be either predefined or user defined. It is typically based on a set of perceptual features which are extracted from the music data. Feature extraction and subsequent music classification are very computational intensive tasks. Today, a variety of music features and possible classification algorithms optimized for various application scenarios and achieving different classification qualities are under discussion. In this paper results concerning the computational needs and the achievable classification rates on different processor architectures are presented. The inspected processors include a general purpose P IV dual core processor, heterogeneous digital signal processor architectures like a Nomadik STn8810 (featuring a smart audio accelerator, SAA) as well as an OMAP2420. In order to increase classification performance, different forms of feature selection strategies (heuristic selection, full search and Mann-Whitney-Test) are applied. Furthermore, the potential of a hardware-based acceleration for this class of application is inspected by performing a fine as well as a coarse grain instruction tree analysis. Instruction trees are identified, which could be attractively implemented as custom instructions speeding up this class of applications.

AB - Today, more and more computational power is available not only in desktop computers but also in portable devices such as smart phones or PDAs. At the same time the availability of huge non-volatile storage capacities (flash memory etc.) suggests to maintain huge music databases even in mobile devices. Automated music classification promises to allow keeping a much better overview on huge data bases for the user. Such a classification enables the user to sort the available huge music archives according to different genres which can be either predefined or user defined. It is typically based on a set of perceptual features which are extracted from the music data. Feature extraction and subsequent music classification are very computational intensive tasks. Today, a variety of music features and possible classification algorithms optimized for various application scenarios and achieving different classification qualities are under discussion. In this paper results concerning the computational needs and the achievable classification rates on different processor architectures are presented. The inspected processors include a general purpose P IV dual core processor, heterogeneous digital signal processor architectures like a Nomadik STn8810 (featuring a smart audio accelerator, SAA) as well as an OMAP2420. In order to increase classification performance, different forms of feature selection strategies (heuristic selection, full search and Mann-Whitney-Test) are applied. Furthermore, the potential of a hardware-based acceleration for this class of application is inspected by performing a fine as well as a coarse grain instruction tree analysis. Instruction trees are identified, which could be attractively implemented as custom instructions speeding up this class of applications.

KW - ASIP

KW - Feature extraction

KW - Music classification

KW - Music information retrieval

KW - Processor architecture optimization

KW - Processor performance

UR - http://www.scopus.com/inward/record.url?scp=58049196537&partnerID=8YFLogxK

U2 - 10.1109/ICSAMOS.2008.4664851

DO - 10.1109/ICSAMOS.2008.4664851

M3 - Conference contribution

AN - SCOPUS:58049196537

SN - 9781424419852

SP - 92

EP - 99

BT - 2008 International Conference on Embedded Computer Systems

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 21 July 2008 through 24 July 2008

ER -

By the same author(s)