%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 11:42:06 AM

@TECHREPORT{Malo_Idiap-RR-08-2019,
         author = {Malo, Grisard and Motlicek, Petr and Allouchi, Wissem and Baeriswyl, Michael and Lazaridis, Alexandros and Zhan, Qingran},
       keywords = {BNF, Deep neural network, Language targets, LID},
       projects = {Idiap, SIIP},
          month = {7},
          title = {SPOKEN LANGUAGE IDENTIFICATION USING LANGUAGE BOTTLENECK FEATURES},
           type = {Idiap-RR},
         number = {Idiap-RR-08-2019},
           year = {2019},
    institution = {Idiap},
        address = {Rue Marconi 19},
       abstract = {In this paper, we introduce a novel approach for Language Identification (LID). Two commonly used state-of-the-art methods based on UBM/GMM I-vector technique, combined with a back-end classifier, are first evaluated. The differential factor between these two methods is the deployment of input features to train the UBM/GMM models: conventional MFCCs, or deep Bottleneck Features (BNF) extracted from a neural network. Analogous to successful algorithms developed for speaker recognition tasks, this paper proposes to train the BNF classifier directly on language targets rather than using conventional phone targets (i.e. international phone alphabet). We show that the proposed approach reduces the number of targets by 96\% when tested 
on 4 languages of SpeechDat databases, which leads to 94\% reduction in training time (i.e. to train BNF classifier). We achieve in average, relative improvement of approximately 35\% in terms of cost average Cavg, as well as language error rates (LER), across all test duration conditions.},
            pdf = {https://publications.idiap.ch/attachments/reports/2019/Malo_Idiap-RR-08-2019.pdf}
}