Acoustic event recognition using dominant spectral basis vectors

Woohyun Choi; Sangwook Park; David K. Han; Hanseok Ko

Acoustic event recognition using dominant spectral basis vectors

Woohyun Choi, Sangwook Park, David K. Han, Hanseok Ko

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper proposes a novel filter bank composed of dominant Spectral Basis Vectors (SBVs) in a spectrogram. Spectral envelopes represented by the SBVs have shown to be excellent characteristic features for discriminating different acoustic events in noisy environment. Non-negative Matrix Factorization (NMF) and non-negative K-SVD (NKSVD) for part-based and holistic representations extract dominant SBVs from a spectrogram. The effectiveness of the proposed method is demonstrated on a database of real life recordings via experiments, and its robust performance is compared to conventional methods.

Original language	English
Pages (from-to)	2002-2006
Number of pages	5
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	2015-January
Publication status	Published - 2015
Event	16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 - Dresden, Germany Duration: 2015 Sept 6 → 2015 Sept 10

Bibliographical note

Publisher Copyright:
Copyright © 2015 ISCA.

Keywords

Acoustic event recognition
Dictionary learning
Dominant spectral basis vector
K-SVD
Non-negative matrix factorization
Robust feature extraction
Spectral envelope

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Signal Processing
Software
Modelling and Simulation

Cite this

@article{eab8fc18563c426c8180729f963d1045,

title = "Acoustic event recognition using dominant spectral basis vectors",

abstract = "This paper proposes a novel filter bank composed of dominant Spectral Basis Vectors (SBVs) in a spectrogram. Spectral envelopes represented by the SBVs have shown to be excellent characteristic features for discriminating different acoustic events in noisy environment. Non-negative Matrix Factorization (NMF) and non-negative K-SVD (NKSVD) for part-based and holistic representations extract dominant SBVs from a spectrogram. The effectiveness of the proposed method is demonstrated on a database of real life recordings via experiments, and its robust performance is compared to conventional methods.",

keywords = "Acoustic event recognition, Dictionary learning, Dominant spectral basis vector, K-SVD, Non-negative matrix factorization, Robust feature extraction, Spectral envelope",

author = "Woohyun Choi and Sangwook Park and Han, {David K.} and Hanseok Ko",

note = "Publisher Copyright: Copyright {\textcopyright} 2015 ISCA.; 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 ; Conference date: 06-09-2015 Through 10-09-2015",

year = "2015",

language = "English",

volume = "2015-January",

pages = "2002--2006",

journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

issn = "2308-457X",

}

TY - JOUR

T1 - Acoustic event recognition using dominant spectral basis vectors

AU - Choi, Woohyun

AU - Park, Sangwook

AU - Han, David K.

AU - Ko, Hanseok

PY - 2015

Y1 - 2015

N2 - This paper proposes a novel filter bank composed of dominant Spectral Basis Vectors (SBVs) in a spectrogram. Spectral envelopes represented by the SBVs have shown to be excellent characteristic features for discriminating different acoustic events in noisy environment. Non-negative Matrix Factorization (NMF) and non-negative K-SVD (NKSVD) for part-based and holistic representations extract dominant SBVs from a spectrogram. The effectiveness of the proposed method is demonstrated on a database of real life recordings via experiments, and its robust performance is compared to conventional methods.

AB - This paper proposes a novel filter bank composed of dominant Spectral Basis Vectors (SBVs) in a spectrogram. Spectral envelopes represented by the SBVs have shown to be excellent characteristic features for discriminating different acoustic events in noisy environment. Non-negative Matrix Factorization (NMF) and non-negative K-SVD (NKSVD) for part-based and holistic representations extract dominant SBVs from a spectrogram. The effectiveness of the proposed method is demonstrated on a database of real life recordings via experiments, and its robust performance is compared to conventional methods.

KW - Acoustic event recognition

KW - Dictionary learning

KW - Dominant spectral basis vector

KW - K-SVD

KW - Non-negative matrix factorization

KW - Robust feature extraction

KW - Spectral envelope

UR - http://www.scopus.com/inward/record.url?scp=84946584270&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84946584270

SN - 2308-457X

VL - 2015-January

SP - 2002

EP - 2006

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

T2 - 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015

Y2 - 6 September 2015 through 10 September 2015

ER -

Acoustic event recognition using dominant spectral basis vectors

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this