Improvement of a speaker authentication system through MLP's post-processing

Speaker verification and utterance verification are examples of techniques that can be used for speaker authentication purposes. Speaker verification consists of accepting or rejecting the claimed identity of a speaker by processing samples of his/her voice. Usually, these systems are based on HMM models that try to represent the characteristics of the talkers' vocal tracts. Utterance verification systems make use of a set of speaker-independent speech models to recognize a certain utterance. If the utterances consist of passwords, this can be used for identity verification purposes. Up to now, both techniques have been used separately. In this paper, we show that combining these two sources of information using neural networks outperforms both the individual classifiers and other proposed methods for combination.