End-to-End DNN Based Speaker Recognition Inspired by i-Vector and PLDA

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130738" target="_blank" >RIV/00216305:26230/18:PU130738 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11724" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11724</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2018.8461958" target="_blank" >10.1109/ICASSP.2018.8461958</a>

Jazyk výsledku

angličtina

Název v původním jazyce

End-to-End DNN Based Speaker Recognition Inspired by i-Vector and PLDA

Popis výsledku v původním jazyce

Recently, several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short utterances. However, for text-independent tasks with longer utterances, end-to-end systems are still outperformed by standard i-vector + PLDA systems. In this work, we develop an end-to-end speaker verification system that is initialized to mimic an i-vector + PLDA baseline. The system is then further trained in an end-to-end manner but regularized so that it does not deviate too far from the initial system. In this way we mitigate overfitting which normally limits the performance of endto- end systems. The proposed system outperforms the i-vector + PLDA baseline on both long and short duration utterances.

Název v anglickém jazyce

End-to-End DNN Based Speaker Recognition Inspired by i-Vector and PLDA

Popis výsledku anglicky

Recently, several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short utterances. However, for text-independent tasks with longer utterances, end-to-end systems are still outperformed by standard i-vector + PLDA systems. In this work, we develop an end-to-end speaker verification system that is initialized to mimic an i-vector + PLDA baseline. The system is then further trained in an end-to-end manner but regularized so that it does not deviate too far from the initial system. In this way we mitigate overfitting which normally limits the performance of endto- end systems. The proposed system outperforms the i-vector + PLDA baseline on both long and short duration utterances.

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

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of ICASSP

ISBN

978-1-5386-4658-8

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

4874-4878

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Calgary

Místo konání akce

Calgary

Datum konání akce

15. 4. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000446384605009