基于比例因子转移概率的AAC音频压缩历史检测算法

AAC compression detection based on scaling factor transition probability

音频压缩历史的检测是音频取证的重要组成部分,对判断音频是否经过篡改和伪造有着十分重要的意义。通过研究发现,AAC音频比例因子的值会随着压缩次数的增加而逐渐减小。基于此,提出了一种基于比例因子转移概率差值统计特性的AAC音频压缩历史检测算法。实验结果表明,该算法能对多次压缩的AAC音频进行准确分类,其低码率转高码率间AAC音频平均分类准确率达到了99.75%,同码率间准确率达97.28%。另外,对比实验也证明了本文算法的性能优于现有算法。

Audio compression history detection is an important part of audio forensics, which is important to detect whether audio has been tampered or forged. An algorithm of AAC audio compression history detection was presented by using the transition probability differences of scale factors as the discriminative feature. Experimental results demonstrate that the proposed method can distinguish the single, double and triple compressed AAC audios effectively, and from the low-bite-rate to high-bit-rate, the average classification accuracy achieves 99.75%, the same-bit-rate detection accuracy achieves 97.28%. In addition, the results of comparison experiments show that the proposed algorithm outperforms the state-of-the-art algorithm.