Přístupnostní navigace
E-application
Search Search Close
Publication detail
MOŠNER, L. PLCHOT, O. ROHDIN, J. BURGET, L. ČERNOCKÝ, J.
Original Title
Speaker Verification with Application-Aware Beamforming
Type
conference paper
Language
English
Original 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.
Keywords
Speaker verification, beamforming, xvector, generalized eigenvalue problem
Authors
MOŠNER, L.; PLCHOT, O.; ROHDIN, J.; BURGET, L.; ČERNOCKÝ, J.
Released
14. 12. 2019
Publisher
IEEE Signal Processing Society
Location
Sentosa, Singapore
ISBN
978-1-7281-0306-8
Book
IEEE Automatic Speech Recognition and Understanding Workshop - Proceedings (ASRU)
Pages from
411
Pages to
418
Pages count
8
URL
https://www.fit.vut.cz/research/publication/12152/
BibTex
@inproceedings{BUT161476, author="Ladislav {Mošner} and Oldřich {Plchot} and Johan Andréas {Rohdin} and Lukáš {Burget} and Jan {Černocký}", title="Speaker Verification with Application-Aware Beamforming", booktitle="IEEE Automatic Speech Recognition and Understanding Workshop - Proceedings (ASRU)", year="2019", pages="411--418", publisher="IEEE Signal Processing Society", address="Sentosa, Singapore", doi="10.1109/ASRU46091.2019.9003932", isbn="978-1-7281-0306-8", url="https://www.fit.vut.cz/research/publication/12152/" }