%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 05:34:47 PM

@INPROCEEDINGS{Madikeri_INTERSPEECH2018_2018,
         author = {Madikeri, Srikanth and Dey, Subhadeep and Motlicek, Petr},
       keywords = {deep neural networks, i-vector, speaker recognition},
       projects = {Idiap},
          title = {Analysis of Language Dependent Front-End for Speaker Recognition},
      booktitle = {Proceedings of Interspeech 2018},
         volume = {1-6},
           year = {2018},
          pages = {1101-1105},
       location = {Hyderabad, INDIA},
           issn = {2308-457X},
           isbn = {978-1-5108-7221-9},
            doi = {10.21437/Interspeech.2018-2071},
       abstract = {In Deep Neural Network (DNN) i-vector based speaker recognition systems, acoustic models trained for Automatic Speech Recognition are employed to estimate sufficient statistics for i-vector modeling. The DNN based acoustic model is typically trained on a wellresourced language like English. In evaluation conditions where enrollment and test data are not in English, as in the NIST SRE 2016 dataset, a DNN acoustic model generalizes poorly. In such conditions, a conventional Universal Background Model/Gaussian Mixture Model (UBM/GMM) based i-vector extractor performs better than the DNN based i-vector system. In this paper, we address the scenario in which one can develop a Automatic Speech Recognizer with limited resources for a language present in the evaluation condition, thus enabling the use of a DNN acoustic model instead of UBM/GMM. Experiments are performed on the Tagalog subset of the NIST SRE 2016 dataset assuming an open training condition. With a DNN i-vector system trained for Tagalog, a relative improvement of 12.1\% is obtained over a baseline system trained for English.}
}