文献类型：期刊文献

英文题名：Perceptual audio hashing algorithm based on Zernike moment and maximum-likelihood watermark detection

作者：Chen, Ning[1];Xiao, Hai-dong[2]

机构：[1]E China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Jiao Tong Univ, Antai Coll Econ & Management, Sino US Global Logist Inst, Shanghai 200030, Peoples R China

年份：2013

卷号：23

期号：4

起止页码：1216

外文期刊名：DIGITAL SIGNAL PROCESSING

收录：;EI(收录号：20132016324117);WOS:【SCI-EXPANDED(收录号:WOS:000319180200015)】；

基金：This work was partly supported by the National Natural Science Foundation of China (60903186, 61271349), by the Fundamental Research Funds for the Central Universities (WH1214015), by the Natural Science Foundation of Shanghai, China (12ZR1415200), and by open funds of the Shanghai Key Laboratory of Information Security Management Technologies (AGK2012008).

语种：英文

外文关键词：Audio hashing algorithm; Maximum-likelihood (ML) watermark detection; Zernike moments

摘要：A new perceptual audio hashing algorithm based on maximum-likelihood watermarking detection is proposed in this paper. The idea is justified by the fact that the maximum-likelihood watermark detector responds similarly to perceptually close audio using a non-embedded watermark (i.e. virtual watermark). The feature vector, which is composed of the total amplitude of low-order Zernike moments of each audio frame, is modeled by the Gaussian or Rayleigh distribution. Then, the maximum-likelihood watermark detection is performed on the feature vector with the virtual watermarks generated by pseudo-random number generator to construct the hash vector. Extensive experiments over three large audio databases of different type (speech, instrumental music, and sung voice) demonstrate the efficiency of the proposed scheme in terms of discrimination, perceptual robustness and identification rate. It is also verified that the proposed scheme outperforms state-of-the-art techniques in perceptual robustness and can be applied in content-based search, successfully. (C) 2013 Elsevier Inc. All rights reserved.