Publication detail
Discriminatively Re-trained i-Vector Extractor For Speaker Recognition
NOVOTNÝ, O. PLCHOT, O. GLEMBEK, O. BURGET, L. MATĚJKA, P.
Original Title
Discriminatively Re-trained i-Vector Extractor For Speaker Recognition
Type
conference paper
Language
English
Original Abstract
In this work we revisit discriminative training of the i-vector extractorcomponent in the standard speaker verification (SV) system. Themotivation of our research lies in the robustness and stability of thislarge generative model, which we want to preserve, and focus itspower towards any intended SV task. We show that after generativeinitialization of the i-vector extractor, we can further refine itwith discriminative training and obtain i-vectors that lead to betterperformance on various benchmarks representing different acousticdomains.
Keywords
i-vectors, i-vector extractor, speaker recogni-tion, speaker verification, discriminative training
Authors
NOVOTNÝ, O.; PLCHOT, O.; GLEMBEK, O.; BURGET, L.; MATĚJKA, P.
Released
12. 5. 2019
Publisher
IEEE Signal Processing Society
Location
Brighton
ISBN
978-1-5386-4658-8
Book
Proceedings of 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Pages from
6031
Pages to
6035
Pages count
5
URL
BibTex
@inproceedings{BUT160000,
author="Ondřej {Novotný} and Oldřich {Plchot} and Ondřej {Glembek} and Lukáš {Burget} and Pavel {Matějka}",
title="Discriminatively Re-trained i-Vector Extractor For Speaker Recognition",
booktitle="Proceedings of 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)",
year="2019",
pages="6031--6035",
publisher="IEEE Signal Processing Society",
address="Brighton",
doi="10.1109/ICASSP.2019.8682590",
isbn="978-1-5386-4658-8",
url="https://ieeexplore.ieee.org/document/8682590"
}Documents