The reliability of Automatic Speaker Recognition (SR) is of the utmost importance for real-world applications. Even if SR systems obtain spectacular performance during evaluation campaigns, several studies have shown the limits and shortcomings of these systems. Reliability first means knowing where and when a system is performing as expected and a research effort is devoted to building confidence measures, by scanning input signals, representations or output scores. Here, a new reliability criterion is presented, dedicated to the latest SR systems based on deep neural network (DNN). The proposed approach uses the set of anchor speakers that controls the learning phase and takes advantage of the structure of the network itself, in order to derive a criterion making it possible to better assess the reliability of the decision based on the extracted speaker embeddings. The relevance and effectiveness of the proposed confidence measure are tested and demonstrated on widely used datasets.
Cite as: Bousquet, P.-M., Rouvier, M., Bonastre, J.-F. (2022) Reliability criterion based on learning-phase entropy for speaker recognition with neural network. Proc. Interspeech 2022, 281-285, doi: 10.21437/Interspeech.2022-8
@inproceedings{bousquet22_interspeech,
author={Pierre-Michel Bousquet and Mickael Rouvier and Jean-Francois Bonastre},
title={{Reliability criterion based on learning-phase entropy for speaker recognition with neural network}},
year=2022,
booktitle={Proc. Interspeech 2022},
pages={281--285},
doi={10.21437/Interspeech.2022-8}
}