SECURITY ISSUES IN SPEECH WATERMARKING FOR INFORMATION TRANSMISSION

The secure transmission of speech information is a significant issue faced by many security professionals and individuals. By applying voice-encryption technique any kind of encrypted sensitive speech data such as password can be transmitted. But this has the serious disadvantage that by means of cryptanalysis attack encrypted data can be compromised. Increasing the strength of encryption/decryption results in an associated increased in the cost. Additional techniques like stenography and digital watermarking can be used to conceal information in an undetectable way in audio data. However this watermarked audio data has to be send through unreliable media and an eavesdropper might get hold of secret message and can also determine the identity of a speaker who is sending the information since human voice contains information based on its characteristics such as frequency, pitch, and energy. This paper proposes Normalized Speech Watermarking technique. Speech signal is normalized to hide the identity of the speaker who is sending the information and then speech watermarking technique is applied on this normalized signal that contains the message (password) so that what information is transmitted should not be unauthorizedly revealed.