User identification and verification are very important aspects of any security system, as imposters find more and more ways to break into even the most complex of security measures. Biometric recognition systems are in demand today due to their reliance of human features that are unique to a person and cannot be forged easily such as face, fingerprints and voice. Like fingerprints, a person's voice has particular unique features and using this voiceprint, their identity can be verified.
The aim of my project is to design and implement a text-independent speaker identification system. Regardless of the language or text used by the speaker, the system should verify his identity. Unique features are extracted using the Hidden Markov Model Toolkit (HTK) and individual speaker models as well as a background model are generated using the Gaussian Mixture Model. Identity of a user is verified by matching features to already created profile, comprised of speech parameters/feature vectors.