Publication Details

Speaker Verification with Application-Aware Beamforming

MOŠNER Ladislav, PLCHOT Oldřich, ROHDIN Johan A., BURGET Lukáš and ČERNOCKÝ Jan. Speaker Verification with Application-Aware Beamforming. In: Proceedings of ASRU 2019. Sentosa, Singapore: IEEE Signal Processing Society, 2019, pp. 411-418. ISBN 978-1-72810-306-8.
Czech title
Rozpoznávání řečníka s aplikačně specifickým směrováním akustického paprsku
Type
conference paper
Language
english
Authors
Mošner Ladislav, Ing. (DCGM FIT BUT)
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Rohdin Johan A., Dr. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, doc. Dr. Ing. (DCGM FIT BUT)
URL
Keywords
Speaker verification, beamforming, xvector, generalized eigenvalue problem
Abstract
Multichannel speech processing applications usually employ beamformers as means of speech enhancement through spatial filtering. Beamformers with learnable parameters require training to minimize a loss function that is not necessarily correlated with the final objective. In this paper, we present a framework employing recent neural network based generalized eigenvalue beamformer and application-specific model that allows for optimization of beamformer w.r.t. target application. In our case, the application is speaker verification which utilizes a speaker embedding (x-vector) extractor that conveniently comes with desired loss. We show that application-specific training of the beamformer brings performance improvements over a system trained in the standard way. We perform our analysis on the recently introduced VOiCES corpus which contains multichannel data and allows us to modify the evaluation trials such that enrollment recordings remain single-channel and test utterances are multichannel.
Published
2019
Pages
411-418
Proceedings
Proceedings of ASRU 2019
Conference
Automatic Speech Recognition and Understanding Workshop 2019, Automatic Speech Recognition and Understanding Workshop 2019, SG
ISBN
978-1-72810-306-8
Publisher
IEEE Signal Processing Society
Place
Sentosa, Singapore, SG
BibTeX 
@INPROCEEDINGS{FITPUB12152,
   author = "Ladislav Mo\v{s}ner and Old\v{r}ich Plchot and A. Johan Rohdin and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Speaker Verification with Application-Aware Beamforming",
   pages = "411--418",
   booktitle = "Proceedings of ASRU 2019",
   year = 2019,
   location = "Sentosa, Singapore, SG",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-72810-306-8",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12152"
}
Back to top