INDIVIDUAL RECOGNITION BY VOICE ANALYSIS

摘要

A person is identified from speech patterns by analyzing his or her utterance to generate a sequence of acoustic feature signals and comparing the utterance feature signals to reference acoustic feature signals characteristic of previously identified speakers. In the identity determination, the best matching of the reference feature signals characteristic of the identified speaker is found for each successive utterance feature signal and a signal representative of the similarity of said best matching feature and the current utterance feature signal is generated. The correspondance of the utterance and the reference acoustic feature signals of the identified speaker is evaluated from the sequence of similarity signals.