Utilizing VOiCES dataset for multichannel speaker verification with beamforming
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F20%3APU136531" target="_blank" >RIV/00216305:26230/20:PU136531 - isvavai.cz</a>
Result on the web
<a href="https://www.isca-speech.org/archive/Odyssey_2020/abstracts/80.html" target="_blank" >https://www.isca-speech.org/archive/Odyssey_2020/abstracts/80.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Odyssey.2020-27" target="_blank" >10.21437/Odyssey.2020-27</a>
Alternative languages
Result language
angličtina
Original language name
Utilizing VOiCES dataset for multichannel speaker verification with beamforming
Original language description
VOiCES from a Distance Challenge 2019 aimed at the evaluation of speaker verification (SV) systems using single-channel trials based on the Voices Obscured in Complex Environmental Settings (VOiCES) corpus. Since it comprises recordings of the same utterances captured simultaneously by multiple microphones in the same environments, it is also suitable for multichannel experiments. In this work, we design a multichannel dataset as well as development and evaluation trials for SV inspired by the VOiCES challenge. Alternatives discarding harmful microphones are presented as well. We asses the utilization of the created dataset for x-vector based SV with beamforming as a front end. Standard fixed beamforming and NN-supported beamforming using simulated data and ideal binary masks (IBM) are compared with another variant of NNsupported beamforming that is trained solely on the VOiCES data. Lack of data revealed by experiments with VOiCESdata trained beamformer was tackled by means of a variant of SpecAugment applied to magnitude spectra. This approach led to as much as 10% relative improvement in EER pushing results closer to those obtained by a good beamformer based on IBMs.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop
ISBN
—
ISSN
2312-2846
e-ISSN
—
Number of pages
7
Pages from-to
187-193
Publisher name
International Speech Communication Association
Place of publication
Tokyo
Event location
Tokyo
Event date
Nov 1, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—