DocumentCode
226970
Title
Audio fingerprinting to identify TV commercial advertisement in real-noisy environment
Author
Jun-Yong Lee ; Hyoung-Gook Kim
Author_Institution
Dept. of Wireless Commun. Eng., Kwangwoon Univ., Seoul, South Korea
fYear
2014
fDate
24-26 Sept. 2014
Firstpage
527
Lastpage
530
Abstract
This paper proposes a high-performance audio fingerprint extraction method for identifying TV commercial advertisement. In the proposed method, a salient audio peak pair fingerprints based on constant Q transform (CQT) are hashed and stored, to be efficiently compared to one another. Experimental results confirm that the proposed method is quite robust in different noise conditions and improves the accuracy of the audio fingerprinting system in real noisy environments.
Keywords
acoustic noise; audio signal processing; feature extraction; television broadcasting; transforms; CQT; TV commercial advertisement identification; audio fingerprinting extraction method; constant Q transform; real-noisy environment; salient audio peak pair fingerprints; Databases; Fingerprint recognition; Noise; Robustness; Servers; TV; Time-frequency analysis; audio content identification; audio fingerprinting; constant Q transform;
fLanguage
English
Publisher
ieee
Conference_Titel
Communications and Information Technologies (ISCIT), 2014 14th International Symposium on
Conference_Location
Incheon
Type
conf
DOI
10.1109/ISCIT.2014.7011969
Filename
7011969
Link To Document