Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis

Shingchern D. You; Ming Jen Hung

doi:10.1109/ICCCI49374.2020.9145984

Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis

Shingchern D. You
, Ming Jen Hung

Department of Computer Science and Information Engineering

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

6 Scopus citations

Abstract

This paper studies the use of independent component analysis (ICA) for reducing the dimensionality of one type of spectro-temporal features, known as the MPEG-7 audio signature descriptors. The dimension-reduced features are used to identify distorted audio items in the experiments. The proposed ICA-based reduction approach is compared with the block average method and the principal component analysis (PCA) method. The experimental results show that features obtained by the ICA approach have higher identification accuracy than comparison counterparts for moderate to highly distorted soundtracks. In this regard, the proposed approach is a better alternative for dimensionality reduction for spectro-temporal features with distortion.

Original language	English
Title of host publication	2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	93-97
Number of pages	5
ISBN (Electronic)	9781728158006
DOIs	https://doi.org/10.1109/ICCCI49374.2020.9145984
State	Published - Jun 2020
Event	2nd International Conference on Computer Communication and the Internet, ICCCI 2020 - Nagoya, Japan Duration: 26 Jun 2020 → 29 Jun 2020

Publication series

Name	2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020

Conference

Conference	2nd International Conference on Computer Communication and the Internet, ICCCI 2020
Country/Territory	Japan
City	Nagoya
Period	26/06/20 → 29/06/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

ICA
MPEG-7 audio signature descriptor
audio identification
dimension reduction

Access to Document

10.1109/ICCCI49374.2020.9145984

Cite this

You, S. D., & Hung, M. J. (2020). Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis. In 2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020 (pp. 93-97). Article 9145984 (2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCCI49374.2020.9145984

You, Shingchern D. ; Hung, Ming Jen. / Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis. 2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 93-97 (2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020).

@inproceedings{efbda19ea5f44b6c81d829a970b146ea,

title = "Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis",

abstract = "This paper studies the use of independent component analysis (ICA) for reducing the dimensionality of one type of spectro-temporal features, known as the MPEG-7 audio signature descriptors. The dimension-reduced features are used to identify distorted audio items in the experiments. The proposed ICA-based reduction approach is compared with the block average method and the principal component analysis (PCA) method. The experimental results show that features obtained by the ICA approach have higher identification accuracy than comparison counterparts for moderate to highly distorted soundtracks. In this regard, the proposed approach is a better alternative for dimensionality reduction for spectro-temporal features with distortion.",

keywords = "ICA, MPEG-7 audio signature descriptor, audio identification, dimension reduction",

author = "You, \{Shingchern D.\} and Hung, \{Ming Jen\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2nd International Conference on Computer Communication and the Internet, ICCCI 2020 ; Conference date: 26-06-2020 Through 29-06-2020",

year = "2020",

month = jun,

doi = "10.1109/ICCCI49374.2020.9145984",

language = "???core.languages.en\_GB???",

series = "2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "93--97",

booktitle = "2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020",

}

You, SD & Hung, MJ 2020, Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis. in 2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020., 9145984, 2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020, Institute of Electrical and Electronics Engineers Inc., pp. 93-97, 2nd International Conference on Computer Communication and the Internet, ICCCI 2020, Nagoya, Japan, 26/06/20. https://doi.org/10.1109/ICCCI49374.2020.9145984

Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis. / You, Shingchern D.; Hung, Ming Jen.
2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 93-97 9145984 (2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020).

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

TY - GEN

T1 - Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis

AU - You, Shingchern D.

AU - Hung, Ming Jen

PY - 2020/6

Y1 - 2020/6

N2 - This paper studies the use of independent component analysis (ICA) for reducing the dimensionality of one type of spectro-temporal features, known as the MPEG-7 audio signature descriptors. The dimension-reduced features are used to identify distorted audio items in the experiments. The proposed ICA-based reduction approach is compared with the block average method and the principal component analysis (PCA) method. The experimental results show that features obtained by the ICA approach have higher identification accuracy than comparison counterparts for moderate to highly distorted soundtracks. In this regard, the proposed approach is a better alternative for dimensionality reduction for spectro-temporal features with distortion.

AB - This paper studies the use of independent component analysis (ICA) for reducing the dimensionality of one type of spectro-temporal features, known as the MPEG-7 audio signature descriptors. The dimension-reduced features are used to identify distorted audio items in the experiments. The proposed ICA-based reduction approach is compared with the block average method and the principal component analysis (PCA) method. The experimental results show that features obtained by the ICA approach have higher identification accuracy than comparison counterparts for moderate to highly distorted soundtracks. In this regard, the proposed approach is a better alternative for dimensionality reduction for spectro-temporal features with distortion.

KW - ICA

KW - MPEG-7 audio signature descriptor

KW - audio identification

KW - dimension reduction

UR - https://www.scopus.com/pages/publications/85094845035

U2 - 10.1109/ICCCI49374.2020.9145984

DO - 10.1109/ICCCI49374.2020.9145984

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85094845035

T3 - 2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020

SP - 93

EP - 97

BT - 2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Computer Communication and the Internet, ICCCI 2020

Y2 - 26 June 2020 through 29 June 2020

ER -

You SD, Hung MJ. Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis. In 2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 93-97. 9145984. (2020 2nd International Conference on Computer Communication and the Internet, ICCCI 2020). doi: 10.1109/ICCCI49374.2020.9145984

Reducing Dimensionality of Spectro-Temporal Data by Independent Component Analysis

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this