Audio Fingerprinting Based on Constant Q Transform for TV Commercial Advertisement Identification

Sang Hyeon Ryu; Hyoung-Gook Kim

doi:10.7776/ASK.2014.33.3.210

All Issue

2014 Vol.33, Issue 3 Preview Page Next Page

Audio Fingerprinting Based on Constant Q Transform for TV Commercial Advertisement Identification TV 광고 식별을 위한 Constant-Q 변환 기반의 오디오 핑거프린팅 방식

31 May 2014. pp. 210-215

PDF XML

Abstract

In spite of distortion caused by noise and echo, the audio fingerprinting technique must identify successfully an audio source. This audio fingerprinting technique is applying for TV commercial advertisement identification. In this paper, we propose a robust audio fingerprinting method for TV commercial advertisement identification. In the proposed method, a prominent audio peak pair fingerprint based on constant Q transform improves the accuracy of the audio fingerprinting system in real noisy environments. Experimental results confirm that the proposed method is quite robust than previous audio fingerprinting method in different noise conditions and achieves promising accurate results.

Keywords

Audio fingerprinting

Modulation constant Q transform

Content identification

Robust matching

오디오 핑거프린팅 기술은 잡음과 에코 등으로 인한 왜곡에도 성공적으로 음원을 식별해야한다. 이러한 오디오 핑거프린팅 기술을 TV광고식별에 적용하고자 한다. 본 논문은 TV 광고 식별을 위한 강인한 오디오 핑거프린팅 방식을 제안한다. 제안된 방법에서 사용되는 Constant Q 변환 기반에서 추출된 현저한 오디오 피크 쌍 핑거프린트는 실제 다양한 잡음환경에서 오디오 핑거프린팅 시스템의 정확도를 향상시키고, 낮은 복잡도를 가진다. 실험결과는 제안된 방식이 기존의 오디오 핑거프린팅 방식에 비해 다양한 잡음환경에서도 안정적이며 신뢰할 수 있는 검색 정확도를 제공함을 보여준다.

키워드

오디오 핑거프린팅

Constant Q 변환

컨텐트 식별

강인한 매칭

References

1.V. Chandrasekhar, M. Sharifi, and D. A. Ross, “Survey and evaluation of audio fingerprinting schemes for mobile query-by-example applications,” in Proc. of 12th ISMIR, 801-806 (2011).

2.A. Wang, “An industrial strength audio search algorithm,” in Proc. of 4th ISMIR, 7-13 (2003).

3.J. Haitsma, and T. Kalker, “A highly robust audio fingerprinting system,” in Proc. of 3rd ISMIR, 107- 115 (2002).

4.X. Pan, X. Yu, J. Deng, W. Yang, and H. Wang, “Audio fingerprinting based on local energy centroid,” IET Int’l CCWMC, 351-354 (2011).

5.T. Jiang, R. Wu, J. Li, K. Xiang, and F. Dai, “A real- time peak discovering method for audio finger-printing,” in Proc. of 5th ICIMCS, 368-371 (2013).

6.M. Park, H. Kim, and S. Yang, “Frequency temporal filtering for a robust audio fingerprinting scheme in real-noise environment,” J. ETRI, 28, 509-512 (2006).

7.W. Son, H.-T. Cho, K. Yoon, and S.-P. Lee, “Sub- fingerprint masking for a robust audio finger-printing system in a real noise environment for portable consumer devices,” IEEE Trans. on CE, 56, 156-169 (2010).

8.X. Anguera, A. Garzon, and T. Adamek, “MASK:robust local feature for audio fingerprinting,” IEEE ICME, 455-460 (2012).

9.M. Malekesmaeili, and R. K. Ward, “A novel local audio fingerprinting algorithm,” IEEE 14th Int'l Workshop on MMSP, 136-140 (2012).

Information

Publisher :The Acoustical Society of Korea
Publisher(Ko) :한국음향학회
Journal Title :The Journal of the Acoustical Society of Korea
Journal Title(Ko) :한국음향학회지
Volume : 33
No :3
Pages :210-215
Received Date : 2013-12-30
Revised Date : 2014-02-10
Accepted Date : 2014-03-18
DOI :https://doi.org/10.7776/ASK.2014.33.3.210

The Journal of the Acoustical Society of KoreaISSN:1225-4428(Print) 2287-3775(Online)한국음향학회

All Issue