logo Idiap Research Institute        
 [BibTeX] [Marc21]
Type of publication: Idiap-RR
Citation: Malo_Idiap-RR-08-2019
Number: Idiap-RR-08-2019
Year: 2019
Month: 7
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.
Keywords: BNF, Deep neural network, Language targets, LID
Projects Idiap
Authors Malo, Grisard
Motlicek, Petr
Allouchi, Wissem
Baeriswyl, Michael
Lazaridis, Alexandros
Zhan, Qingran
Crossref by Grisard_TSD2019_2019
Added by: [ADM]
Total mark: 0
  • Malo_Idiap-RR-08-2019.pdf (MD5: 0a2b2f6a9eb106dada1a79669328d78c)