Subspace projection cepstral coefficients for noise robust acoustic event recognition

Sangwook Park, Younglo Lee, David K. Han, Hanseok Ko

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, a novel feature for noise robust sound event recognition is proposed. The proposed feature is obtained by a two-step procedure. First, a subspace bank is established via target event analysis in complex vector space. Then, by projecting observation vectors onto the subspace bank, noise effect can be reduced while generating discriminant characters originated from differing event subspaces. To demonstrate robustness of the proposed feature, experiments with several classifiers were conducted with varying SNR cases under four noisy environments. According to the experimental results, the proposed method has shown superior performance over prominent conventional methods.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages761-765
Number of pages5
ISBN (Electronic)9781509041176
DOIs
Publication statusPublished - 2017 Jun 16
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: 2017 Mar 52017 Mar 9

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period17/3/517/3/9

Fingerprint

Vector spaces
Acoustic noise
Classifiers
Acoustics
Acoustic waves
Experiments

Keywords

  • acoustic event classification
  • principal component analysis
  • robust feature extraction
  • subspace learning

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Park, S., Lee, Y., Han, D. K., & Ko, H. (2017). Subspace projection cepstral coefficients for noise robust acoustic event recognition. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 761-765). [7952258] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952258

Subspace projection cepstral coefficients for noise robust acoustic event recognition. / Park, Sangwook; Lee, Younglo; Han, David K.; Ko, Hanseok.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 761-765 7952258.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Park, S, Lee, Y, Han, DK & Ko, H 2017, Subspace projection cepstral coefficients for noise robust acoustic event recognition. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952258, Institute of Electrical and Electronics Engineers Inc., pp. 761-765, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 17/3/5. https://doi.org/10.1109/ICASSP.2017.7952258
Park S, Lee Y, Han DK, Ko H. Subspace projection cepstral coefficients for noise robust acoustic event recognition. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 761-765. 7952258 https://doi.org/10.1109/ICASSP.2017.7952258
Park, Sangwook ; Lee, Younglo ; Han, David K. ; Ko, Hanseok. / Subspace projection cepstral coefficients for noise robust acoustic event recognition. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 761-765
@inproceedings{598b864e8ce84b3e94a2c97ca78f0e48,
title = "Subspace projection cepstral coefficients for noise robust acoustic event recognition",
abstract = "In this paper, a novel feature for noise robust sound event recognition is proposed. The proposed feature is obtained by a two-step procedure. First, a subspace bank is established via target event analysis in complex vector space. Then, by projecting observation vectors onto the subspace bank, noise effect can be reduced while generating discriminant characters originated from differing event subspaces. To demonstrate robustness of the proposed feature, experiments with several classifiers were conducted with varying SNR cases under four noisy environments. According to the experimental results, the proposed method has shown superior performance over prominent conventional methods.",
keywords = "acoustic event classification, principal component analysis, robust feature extraction, subspace learning",
author = "Sangwook Park and Younglo Lee and Han, {David K.} and Hanseok Ko",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/ICASSP.2017.7952258",
language = "English",
pages = "761--765",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Subspace projection cepstral coefficients for noise robust acoustic event recognition

AU - Park, Sangwook

AU - Lee, Younglo

AU - Han, David K.

AU - Ko, Hanseok

PY - 2017/6/16

Y1 - 2017/6/16

N2 - In this paper, a novel feature for noise robust sound event recognition is proposed. The proposed feature is obtained by a two-step procedure. First, a subspace bank is established via target event analysis in complex vector space. Then, by projecting observation vectors onto the subspace bank, noise effect can be reduced while generating discriminant characters originated from differing event subspaces. To demonstrate robustness of the proposed feature, experiments with several classifiers were conducted with varying SNR cases under four noisy environments. According to the experimental results, the proposed method has shown superior performance over prominent conventional methods.

AB - In this paper, a novel feature for noise robust sound event recognition is proposed. The proposed feature is obtained by a two-step procedure. First, a subspace bank is established via target event analysis in complex vector space. Then, by projecting observation vectors onto the subspace bank, noise effect can be reduced while generating discriminant characters originated from differing event subspaces. To demonstrate robustness of the proposed feature, experiments with several classifiers were conducted with varying SNR cases under four noisy environments. According to the experimental results, the proposed method has shown superior performance over prominent conventional methods.

KW - acoustic event classification

KW - principal component analysis

KW - robust feature extraction

KW - subspace learning

UR - http://www.scopus.com/inward/record.url?scp=85023750845&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023750845&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952258

DO - 10.1109/ICASSP.2017.7952258

M3 - Conference contribution

AN - SCOPUS:85023750845

SP - 761

EP - 765

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -