Feature selection for a fast speaker detection system with neural networks and Genetic Algorithms

Today, there is a great necessity for security systems in banks, laboratories, etc.; specially those that have restricted areas or expensive equipment. Most of the time people use magnetic cards or similar technologies. However, these kind of devices can be vulnerable, because these might be used by intruders in case of a misplaced device. More advanced technologies use iris or voice detection, potentially increasing the security level against intruders. This work is focused on the latter group. This paper proposes a hybrid method, for the speech processing area, to select and extract the best features that represent a speech sample. The proposed method makes use of a Genetic Algorithm along with Feed Forward Neural Networks in order to either deny or accept personal access in real time. Finally, to test the proposed method, a series of experiments were conducted, by using fifteen different speakers; obtaining an efficiency rate of up to 97% on intruder detection.