Biometric Identity Verification using Automatic Speaker Recognition

Password based Security Systems have to provide Authentication and Privacy. Strong privacy protected and high security authentication System design remains as an open problem because of the weak passwords. The fundamental problem in normal text-based passwords is that weak passwords are vulnerable to attacks and strong passwords creating problem for the user as he has to remember them with difficulty. Biometric features like passwords uttered by speakers are well suited for authentication, as this cannot be stolen or recreated and is unique to each individual. Biometric Identity Verification using Automatic Speaker Recognition is the neural network based process of automatically recognizing the user from a recording, using the text-dependent password uttered by speech. Here, Biometric identity verification is the speech that can be used to either accept or reject the identity claimed by a given user. Text supports user to remember the password when he forgets and also even when revealed to others it does not harm the system as it takes only voice password from authorized user. Voice is considered a valuable biometric feature which depends on the specific person´s speaking style and physical attributes, and also it is very easy to collect and process speech data. The capacity of proposed security framework is to have a framework that will just open after perceiving a voice secret word talked by the watchword holder utilizing an Artificial Neural Network.