%Aigaion2 BibTeX export from Idiap Publications
%Tuesday 18 June 2024 12:05:40 PM

@INPROCEEDINGS{Espuna_ODYSSEY2024_2024,
         author = {Espu{\~{n}}a, Aleix and Prasad, Amrutha and Motlicek, Petr and Madikeri, Srikanth and Christof, Sch{\"{u}}pbach},
       projects = {Idiap, armasuisse},
          title = {Normalizing Flows for Speaker and Language Recognition Backend},
      booktitle = {Odyssey 2024: The Speaker and Language Recognition Workshop},
           year = {2024},
       abstract = {In this paper, we address the Gaussian distribution assumption made in PLDA, a popular back-end classifier used in Speaker and Language recognition tasks. We study normalizing flows, which allow using non-linear transformations and still obtain a model that can explicitly represent a probability density. The model makes no assumption about the distribution of the observations. This alleviates the need for length normalization, a well known data preprocessing step used to boost PLDA performance. We demonstrate the effectiveness of this flow model on NIST SRE16, LRE17 and LRE22 datasets. We observe that when applying length normalization, both the flow model and PLDA achieve similar EERs for SRE16 (11.5\% vs 11.8\%). However, when length normalization is not applied, the flow shows more robustness and offers better EERs (13.1\% vs 17.1\%). For LRE17 and LRE22, the best classification accuracies (84.2\%, 75.5\%) are obtained by the flow model without any need for length normalization.}
}