Dereverberation and Beamforming in Far-Field Speaker Recognition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130731" target="_blank" >RIV/00216305:26230/18:PU130731 - isvavai.cz</a>
Result on the web
<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11717" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11717</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP.2018.8462365" target="_blank" >10.1109/ICASSP.2018.8462365</a>
Alternative languages
Result language
angličtina
Original language name
Dereverberation and Beamforming in Far-Field Speaker Recognition
Original language description
This paper deals with far-field speaker recognition. On a corpus of NIST SRE 2010 data retransmitted in a real room with multiple microphones, we first demonstrate how room acoustics cause significant degradation of state-of-the-art ivector based speaker recognition system. We then investigate several techniques to improve the performances ranging from probabilistic linear discriminant analysis (PLDA) re-training, through dereverberation, to beamforming. We found that weighted prediction error (WPE) based dereverberation combined with generalized eigenvalue beamformer with powerspectral density (PSD) weighting masks generated by neural networks (NN) provides results approaching the clean closemicrophone setup. Further improvement was obtained by re-training PLDA or the mask-generating NNs on simulated target data. The work shows that a speaker recognition system working robustly in the far-field scenario can be developed.
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
2018
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 ICASSP 2018
ISBN
978-1-5386-4658-8
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
5254-5258
Publisher name
IEEE Signal Processing Society
Place of publication
Calgary
Event location
Calgary
Event date
Apr 15, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000446384605085