Speaker Verification with Application-Aware Beamforming

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134976" target="_blank" >RIV/00216305:26230/19:PU134976 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.fit.vut.cz/research/publication/12152/" target="_blank" >https://www.fit.vut.cz/research/publication/12152/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Speaker Verification with Application-Aware Beamforming

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Speaker Verification with Application-Aware Beamforming

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of ASRU 2019

ISBN

978-1-7281-0306-8

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

411-418

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Sentosa, Singapore

Místo konání akce

Automatic Speech Recognition and Understanding W

Datum konání akce

13. 11. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—