Publication Details
Analysis of the DNN-Based SRE Systems in Multi-language Conditions
Matějka Pavel, Ing., Ph.D. (DCGM)
Glembek Ondřej, Ing., Ph.D.
Plchot Oldřich, Ing., Ph.D. (DCGM)
Grézl František, Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
DNN, Multi-Language, Speaker Recognition
This paper analyzes the behavior of our state-of-the-art Deep Neural Network/i-vector/PLDA-based speaker recognition systems in multi-language conditions. On the "Language Pack" of the PRISM set, we evaluate the systems performance using the NISTs standard metrics. We show that not only the gain from using DNNs vanishes, nor using dedicated DNNs for target conditions helps, but also the DNN-based systems tend to produce de-calibrated scores under the studied conditions. This work gives suggestions for directions of future research rather than any particular solutions to these issues.
In this work, we have studied the behavior of the DNN techniques in SRE i-vector/PLDA systems, currently considered to be state-ofthe- art, as evaluated on the most common NIST SRE English test sets, such as the NIST SRE 2010, condition 5.
@inproceedings{BUT132603,
author="Ondřej {Novotný} and Pavel {Matějka} and Ondřej {Glembek} and Oldřich {Plchot} and František {Grézl} and Lukáš {Burget} and Jan {Černocký}",
title="Analysis of the DNN-Based SRE Systems in Multi-language Conditions",
booktitle="Proceedings of SLT 2016",
year="2016",
pages="199--204",
publisher="IEEE Signal Processing Society",
address="San Diego",
doi="10.1109/slt.2016.7846265",
isbn="978-1-5090-4903-5",
url="http://ieeexplore.ieee.org/document/7846265/"
}