A Novel Non-repudiate Scheme with Voice FeatureMarking

A digital watermark is the type of latent indicator secretly embedded in a noise-tolerant signal such as audio or image data. It is typically used to identify the ownership or copyright of material. “Watermarking” is the process of hiding digital information in a carrier signal in order to confirm the authenticity or integrity of the carrier signal as well as show the identity of its owners. Since a digital copy of data is the same as the original, digital watermarking is a passive protection tool. This technique simply marks the signal with the data neither it degrades nor it controls access to the data, thereby securing the communication. The proposed system introduces a novel non-repudiate scheme to ensure the ownership of every audio communication. This method embeds the prepared watermark in the transform domain of the audio signal using the fast Walsh transforms. Watermark used in this technique is unique for each member, and thus, it provides additional authenticity in every communication compared to state of the art.