Steganalysis of analysis-by-synthesis speech exploiting pulse-position distribution characteristics
Hui Tian, Yanpeng Wu, Chin-Chen Chang, Yongfeng Huang, Jin Liu, Tian Wang, Yonghong Chen and Yiqiao Cai
Article first published online: 2 FEB 2016 | DOI: 10.1002/sec.1443
We present a support-vector-machine-based steganalysis of low bit-rate speech exploiting statistic characteristics of pulse positions. Specifically, we utilize the probability distribution of pulse positions as a long-time distribution feature, extract Markov transition probabilities of pulse positions according to the short-time invariance characteristic of speech signals, and employ joint probability matrices to characterize the pulse-to-pulse correlation. The experimental results demonstrate that the proposed method significantly outperforms the previous ones on detection accuracy, false positive rate, and false negative rate.