Robust audio surveillance using spectrogram image texture feature

Roneel V. Sharan; Tom J. Moir

doi:10.1109/ICASSP.2015.7178312

Robust audio surveillance using spectrogram image texture feature

Roneel V. Sharan, Tom J. Moir

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

8 Citations (Scopus)

Abstract

A sound signal produces a unique texture which can be visualized using a spectrogram image and analyzed for automatic sound recognition. In this paper, we explore the use of a well-known image texture analysis technique called the gray-level co-occurrence matrix (GLCM) for sound recognition in an audio surveillance application. The GLCM captures the distribution of co-occurring values at a given offset. Unlike most other similar research which derive features from the GLCM, we use the matrix values itself to form the feature vector with analysis carried out in subbands. When compared to a baseline feature from related work, the proposed spectrogram image texture feature (SITF) gives marginally lower results under clean and high signal-to-noise ratio (SNR) conditions but significantly better results are achieved at low SNR, where the baseline feature was seen to be less effective.

Original language	English
Title of host publication	2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1956-1960
Number of pages	5
Volume	2015-August
ISBN (Electronic)	9781467369978
DOIs	https://doi.org/10.1109/ICASSP.2015.7178312
Publication status	Published - 1 Jan 2015
Externally published	Yes
Event	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: 19 Apr 2014 → 24 Apr 2014

Conference

Conference	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Country/Territory	Australia
City	Brisbane
Period	19/04/14 → 24/04/14

Keywords

Audio surveillance
gray-level cooccurrence matrix
sound recognition
spectrogram image texture feature
support vector machine

Access to Document

10.1109/ICASSP.2015.7178312

Cite this

@inproceedings{5d5badedf8034344916ace966a129769,

title = "Robust audio surveillance using spectrogram image texture feature",

abstract = "A sound signal produces a unique texture which can be visualized using a spectrogram image and analyzed for automatic sound recognition. In this paper, we explore the use of a well-known image texture analysis technique called the gray-level co-occurrence matrix (GLCM) for sound recognition in an audio surveillance application. The GLCM captures the distribution of co-occurring values at a given offset. Unlike most other similar research which derive features from the GLCM, we use the matrix values itself to form the feature vector with analysis carried out in subbands. When compared to a baseline feature from related work, the proposed spectrogram image texture feature (SITF) gives marginally lower results under clean and high signal-to-noise ratio (SNR) conditions but significantly better results are achieved at low SNR, where the baseline feature was seen to be less effective.",

keywords = "Audio surveillance, gray-level cooccurrence matrix, sound recognition, spectrogram image texture feature, support vector machine",

author = "Sharan, {Roneel V.} and Moir, {Tom J.}",

year = "2015",

month = jan,

day = "1",

doi = "10.1109/ICASSP.2015.7178312",

language = "English",

volume = "2015-August",

pages = "1956--1960",

booktitle = "2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 ; Conference date: 19-04-2014 Through 24-04-2014",

}

Sharan, RV & Moir, TJ 2015, Robust audio surveillance using spectrogram image texture feature. in 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. vol. 2015-August, 7178312, Institute of Electrical and Electronics Engineers (IEEE), pp. 1956-1960, 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015, Brisbane, Australia, 19/04/14. https://doi.org/10.1109/ICASSP.2015.7178312

Robust audio surveillance using spectrogram image texture feature. / Sharan, Roneel V.; Moir, Tom J.
2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Vol. 2015-August Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 1956-1960 7178312.

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

TY - GEN

T1 - Robust audio surveillance using spectrogram image texture feature

AU - Sharan, Roneel V.

AU - Moir, Tom J.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - A sound signal produces a unique texture which can be visualized using a spectrogram image and analyzed for automatic sound recognition. In this paper, we explore the use of a well-known image texture analysis technique called the gray-level co-occurrence matrix (GLCM) for sound recognition in an audio surveillance application. The GLCM captures the distribution of co-occurring values at a given offset. Unlike most other similar research which derive features from the GLCM, we use the matrix values itself to form the feature vector with analysis carried out in subbands. When compared to a baseline feature from related work, the proposed spectrogram image texture feature (SITF) gives marginally lower results under clean and high signal-to-noise ratio (SNR) conditions but significantly better results are achieved at low SNR, where the baseline feature was seen to be less effective.

AB - A sound signal produces a unique texture which can be visualized using a spectrogram image and analyzed for automatic sound recognition. In this paper, we explore the use of a well-known image texture analysis technique called the gray-level co-occurrence matrix (GLCM) for sound recognition in an audio surveillance application. The GLCM captures the distribution of co-occurring values at a given offset. Unlike most other similar research which derive features from the GLCM, we use the matrix values itself to form the feature vector with analysis carried out in subbands. When compared to a baseline feature from related work, the proposed spectrogram image texture feature (SITF) gives marginally lower results under clean and high signal-to-noise ratio (SNR) conditions but significantly better results are achieved at low SNR, where the baseline feature was seen to be less effective.

KW - Audio surveillance

KW - gray-level cooccurrence matrix

KW - sound recognition

KW - spectrogram image texture feature

KW - support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84943810354&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2015.7178312

DO - 10.1109/ICASSP.2015.7178312

M3 - Conference proceeding contribution

AN - SCOPUS:84943810354

VL - 2015-August

SP - 1956

EP - 1960

BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

Y2 - 19 April 2014 through 24 April 2014

ER -

Robust audio surveillance using spectrogram image texture feature

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this