Detail publikace

Analysis of the DNN-Based SRE Systems in Multi-language Conditions

NOVOTNÝ, O. MATĚJKA, P. GLEMBEK, O. PLCHOT, O. GRÉZL, F. BURGET, L. ČERNOCKÝ, J.

Originální název

Analysis of the DNN-Based SRE Systems in Multi-language Conditions

Anglický název

Analysis of the DNN-Based SRE Systems in Multi-language Conditions

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

Dokumenty

BibTex


@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",
  annote="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.",
  address="IEEE Signal Processing Society",
  booktitle="Proceedings of SLT 2016",
  chapter="132603",
  doi="10.1109/slt.2016.7846265",
  edition="NEUVEDEN",
  howpublished="electronic, physical medium",
  institution="IEEE Signal Processing Society",
  year="2016",
  month="december",
  pages="199--204",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}