Speech Perceptual Hashing Authentication Algorithm Based on Spectral Subtraction and Energy to Entropy Ratio

In order to meet the requirements of robustness and discrimination of content preserving operations after conversion of speech communication format on the heterogeneous mobile terminal, and noise reduction and efficient authentication, a new efficient speech perceptual hashing authentication algorithm based on spectral subtraction and energy to entropy ratio was proposed. Firstly the proposed algorithm uses spectral subtraction method to denoise the speech signals which processed by applying pre-processing. Secondly, the energy to entropy value matrix of each frame is obtained by applying the method of energy to entropy ratio. Finally, the binary perceptual hash sequence is generated. Experiment results show that the proposed algorithm can denoise the speech effectively, and have good robustness and discrimination to content preserving operations, as well as having high efficiency and good ability to implement tamper detection.