Steganalysis of Analysis-by-synthesis Compressed Speech
In this paper a steganalysis method for analysis-bysynthesis (AbS) compressed speech is proposed. In the steganalysis method, the probability difference of 0 and 1 and five statistics, including sum of histogram local flatness, sum of histogram local extremum difference, sum of histogram local variance, sum of histogram characteristic function, are used as distinguishing features. SVM classifiers are employed to discriminate stego speech from cover speech. For the example of steganalysis to speech compressed by G.729 algorithm, experiment results show the proposed algorithm has good performance.
Steganalysis Compressed speech Analysis-bysynthesis Pulse position parameters Statistics
Qi Ding
Zhengzhou Information Science and Technology Institute Zhengzhou, People’s Republic of China
国际会议
南京
英文
681-685
2010-11-01（万方平台首次上网日期，不代表论文的发表时间）