International Journal of Computer Science & Information Technology (IJCSIT) Vol 8, No 4, August 2016 DOI:10.5121/ijcsit.2016.8406 61 ADAPTIVE WATERMARKING TECHNIQUE FOR SPEECH SIGNAL AUTHENTICATION Dr. Methaq Talib Gaata and Refah Aamer Jaafar Computer Science Department, University of Mustansiriyah, Baghdad, Iraq ABSTRACT Biometrics data recently has become a major role in determining the identity of the person. With such importance for the use of biometrics data, there are many attacks that threaten the security and integrity of biometrics data itself. Therefore, it becomes necessary to protect the originality of biometrics data against manipulation and fraud. This paper presents an authentication technique to achieve the authenticity of speech signals based on adaptive watermarking technique. The basic idea is depends on extracting the speech features from the speech signal initially and then using these features as a watermark. The watermark information embeds into the same speech signal. The short time energy technique is used to identifying the suitable positions for embedding the watermark in order to avoid the regions that used in the speech recognition system. After exclusion the important areas that used in speech recognition the Genetic Algorithm (GA) is used to generate random locations to hide the watermark information in an intelligent manner. The experimental results have achieved high efficiency in establishing the authenticity of speech signal and the process of embedding watermark not effect on features that used in speech recognition. KEYWORDS Adaptive Watermarking, Biometric, Speech Processing, Genetic Algorithm 1. INTRODUCTION Biometric technology has a basic rule for determining the identity of the person, and forms the front of the systems that require precise identity. Also use of biometric systems conveniently significantly (there is no need to carry or remember such passwords and cannot stolen, cannot replace compared with traditional systems). Biometric systems based on physiological and behavioral characteristics of the person such as fingerprint, iris, retina, facial, speech, signature, etc. The biometric systems could work properly only when the biometrics data that entered to the systems are from legitimate source and when sure the biometrics data has not tampered. Therefore, the authentication of biometrics data is of important research issues for protection against tampered attacks [1]. Cryptography and watermarking techniques are among potential techniques to ensure the authentication of biometrics data. The techniques of cryptography introduce a high level of security but need a high time complexity and also do not provide any level of security when the biometrics data is decrypted. On the contrary, the techniques of watermarking based on embedding watermark information into the biometrics data itself without degrading to their features which used through the process of determining the identity of the authorized person. Therefore, it offers authentication of biometrics data even after the decryption process. As a result, a watermarking techniques is usually imperceptible, robust to unauthorized persons and capable of detect any trying to tamper for achieving the authentication of biometrics data [2].