This work presents an analysis of i-vectors for speaker recognition working with short utterances and methods to alleviate the loss of performance these utterances imply. Our research reveals that this degradation is strongly influenced by the phonetic mismatch between enrollment and test utterances. However, this mismatch is unused in the standard i-vector PLDA framework. It is proposed a metric to measure this phonetic mismatch and a simple yet effective compensation for the standard i-vector PLDA speaker verification framework. Our results, carried out in NIST SRE10 coreext-coreext female det. 5, evidence relative improvements up to 6.65% in short utterances, and up to 9.84% in long utterances.
Cite as: Viñals, I., Ortega, A., Miguel, A., Lleida, E. (2018) Phonetic Variability Influence on Short Utterances in Speaker Verification. Proc. IberSPEECH 2018, 6-9, doi: 10.21437/IberSPEECH.2018-2
@inproceedings{vinals18_iberspeech,
author={Ignacio Viñals and Alfonso Ortega and Antonio Miguel and Eduardo Lleida},
title={{Phonetic Variability Influence on Short Utterances in Speaker Verification}},
year=2018,
booktitle={Proc. IberSPEECH 2018},
pages={6--9},
doi={10.21437/IberSPEECH.2018-2}
}