대한전기학회:학술대회논문집 (Proceedings of the KIEE Conference)
- 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
- /
- Pages.2101-2102
- /
- 2006
신경망과 HAS을 이용한 강인한 오디오 워터마킹 알고리즘
Robust Audio Watermarking Using HAS and Neural Network
- Jung, Se-Won (Department of Information Engineering Myongji University) ;
- Piao, Cheng-Ri (Department of Information Engineering Myongji University) ;
-
Han, Seung-Soo
(Department of Information Engineering Myongji University)
- 발행 : 2006.07.12
초록
In this paper, a new digital audio watermarking algorithm is presented. The proposed algorithm embeds watermark into audio signal based on human auditory system (HAS). This algorithm is a blind audio watermarking method, which does not require any prior information during watermark extraction process. This algorithm finds watermarking position using time-domain masking effect. First we insert the watermark into wavelet domain, and then we use a back-propagation neural network (BPN) to learn the characteristics of relationship between the watermark and the watermarked audio. Due to the teaming and adaptive capabilities of the BPN, the false recovery of the watermark can be greatly reduced by the trained BPN. Experimental results show that the proposed method has good inaudibility and high robustness to common audio processing attacks.
키워드