In this paper, we present a novel architecture for a Speaker Recognition system over the telephone. The proposed system introduces acoustic information into a HMM-based recognizer. This is achieved by using a phonetic classifier during the training phase. Three broad phonetic classes: voiced frames, unvoiced frames and transitions, are defined. We design speaker templates by the parallel connection of the outputs of the single state HMM´s and by the combination of the single state HMM's into a four state HMM after estimation of the transition probabilities. The results show that this architecture performs better than others without phonetic classification.
Cite as: Rodriguez-Linares, L., Garcia-Mateo, C. (1997) On the use of acoustic segmentation in speaker identification. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 2315-2318, doi: 10.21437/Eurospeech.1997-609
@inproceedings{rodriguezlinares97_eurospeech,
author={Leandro Rodriguez-Linares and Carmen Garcia-Mateo},
title={{On the use of acoustic segmentation in speaker identification}},
year=1997,
booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
pages={2315--2318},
doi={10.21437/Eurospeech.1997-609}
}