On the use of X-vectors for Robust Speaker Recognition
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130767" target="_blank" >RIV/00216305:26230/18:PU130767 - isvavai.cz</a>
Výsledek na webu
<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11787" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11787</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Odyssey.2018-24" target="_blank" >10.21437/Odyssey.2018-24</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
On the use of X-vectors for Robust Speaker Recognition
Popis výsledku v původním jazyce
Text-independent speaker verification (SV) is currently in the process of embracing DNN modeling in every stage of SV system. Slowly, the DNN-based approaches such as end-to-end modelling and systems based on DNN embeddings start to be competitive even in challenging and diverse channel conditions of recent NIST SREs. Domain adaptation and the need for a large amount of training data are still a challenge for current discriminative systems and (unlike with generative models), we see significant gains from data augmentation, simulation and other techniques designed to overcome lack of training data. We present an analysis of a SV system based on DNN embeddings (x-vectors) and focus on robustness across diverse data domains such as standard telephone and microphone conversations, both in clean, noisy and reverberant environments. We also evaluate the system on challenging far-field data created by re-transmitting a subset of NIST SRE 2008 and 2010 microphone interviews. We compare our results with the stateof- the-art i-vector system. In general, we were able to achieve better performance with the DNN-based systems, but most importantly, we have confirmed the robustness of such systems across multiple data domains.
Název v anglickém jazyce
On the use of X-vectors for Robust Speaker Recognition
Popis výsledku anglicky
Text-independent speaker verification (SV) is currently in the process of embracing DNN modeling in every stage of SV system. Slowly, the DNN-based approaches such as end-to-end modelling and systems based on DNN embeddings start to be competitive even in challenging and diverse channel conditions of recent NIST SREs. Domain adaptation and the need for a large amount of training data are still a challenge for current discriminative systems and (unlike with generative models), we see significant gains from data augmentation, simulation and other techniques designed to overcome lack of training data. We present an analysis of a SV system based on DNN embeddings (x-vectors) and focus on robustness across diverse data domains such as standard telephone and microphone conversations, both in clean, noisy and reverberant environments. We also evaluate the system on challenging far-field data created by re-transmitting a subset of NIST SRE 2008 and 2010 microphone interviews. We compare our results with the stateof- the-art i-vector system. In general, we were able to achieve better performance with the DNN-based systems, but most importantly, we have confirmed the robustness of such systems across multiple data domains.
Klasifikace
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)
Návaznosti výsledku
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)
Ostatní
Rok uplatnění
2018
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of Odyssey 2018
ISBN
—
ISSN
2312-2846
e-ISSN
—
Počet stran výsledku
8
Strana od-do
168-175
Název nakladatele
International Speech Communication Association
Místo vydání
Les Sables d´Olonne
Místo konání akce
Les Sables d'Olonne, France
Datum konání akce
26. 6. 2018
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—