Conceptual authentication speech hashing base upon hypotrochoid graph
Mahdi Nouri, Nooshin Farhangian, Zahra Zeinolabedini, Mahyar Safarinia · 2012
The speech hash function which maps speech to a short binary string based on the speech's perceptual properties, is proposed as a new solution for automated speech indexing and speech content authentication. In general, the speech hash function needs to have two properties: discrimination, which means that perceptually distinct speech clips must have different hash vectors, and perceptual robustness, which means that perceptually identical speech clips must have the same hash vector. A different key-dependent robust speech hashing based upon speech construction model is proposed in this article. The proposed hash function is based on the essential frequency series. Robust hash is calculated based on linear spectrum frequencies which model the verbal territory. The correlation between LSFs is decoupled by discrete wavelet transformation (DWT). A randomization structure controlled by a secret key is used in hash generation for random feature selection. The hash function is key-dependent and collision resistant. Temporarily, it is extremely robust to content protective operations besides having high accuracy of tampering localization. They are found, the first, to perform very adequately in identification and verification tests, and the second, to be very robust to a large range of attacks. Furthermore, it can be addressed the issue of security of hashes and proposed a keying technique, and thereby a key-dependent hash function.