An improved technique for voice-based security systems

摘要

A voice-based security system requires that a series of utterances to be uttered by the requester contain at least one repeated utterance. The system compares a representation of each instance of the repeated utterance as uttered by the requester to both a prestored template for the utterance and to each representation of the other instances of the utterance as uttered by said requester. The requester is authenticated only if each representation of the repeated utterance as uttered by said requester matches the prestored template and the representations of the repeated utterance as uttered by said requester do not match each other to such a high degree that they are deemed to have been mechanically generated.