Publication Details

BUT Text-Dependent Speaker Verification System for SdSV Challenge 2020

LOZANO DÍEZ, A.; SILNOVA, A.; PULUGUNDLA, B.; ROHDIN, J.; VESELÝ, K.; BURGET, L.; PLCHOT, O.; GLEMBEK, O.; NOVOTNÝ, O.; MATĚJKA, P. BUT Text-Dependent Speaker Verification System for SdSV Challenge 2020. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Proceedings of Interspeech. Shanghai: International Speech Communication Association, 2020. p. 761-765. ISSN: 1990-9772.

Czech title

Systém VUT pro ověřování mluvčího závislý na textu pro SdSV Challenge 2020

Type

conference paper

Language

English

Authors

Lozano Díez Alicia, Ph.D.
Silnova Anna, M.Sc., Ph.D. (DCGM)
Pulugundla Bhargav, M.Sc.
Rohdin Johan Andréas, M.Sc., Ph.D. (DCGM)
Veselý Karel, Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Plchot Oldřich, Ing., Ph.D. (DCGM)
Glembek Ondřej, Ing., Ph.D.
Novotný Ondřej, Ing., Ph.D.
Matějka Pavel, Ing., Ph.D. (DCGM)

URL

Keywords

text-dependent speaker verification, phrasedependent PLDA, phrase recognizer

Abstract

In this paper, we present the winning BUT submission for the text-dependent task of the SdSV challenge 2020. Given the large amount of training data available in this challenge, we explore successful techniques from text-independent systems in the text-dependent scenario. In particular, we trained x-vector extractors on both in-domain and out-of-domain datasets and combine them with i-vectors trained on concatenated MFCCs and bottleneck features, which have proven effective for the text-dependent scenario. Moreover, we proposed the use of phrase-dependent PLDA backend for scoring and its combination with a simple phrase recognizer, which brings up to 63% relative improvement on our development set with respect to using standard PLDA. Finally, we combine our different i-vector and x-vector based systems using a simple linear logistic regression score level fusion, which provides 28% relative improvement on the evaluation set with respect to our best single system.

Published

2020

Pages

761–765

Journal

Proceedings of Interspeech, vol. 2020, no. 10, ISSN 1990-9772

Proceedings

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Publisher

International Speech Communication Association

Place

Shanghai

DOI

10.21437/Interspeech.2020-2882

UT WoS

000833594100158

EID Scopus

2-s2.0-85098107319

BibTeX

@inproceedings{BUT168145,
  author="Alicia {Lozano Díez} and Anna {Silnova} and Bhargav {Pulugundla} and Johan Andréas {Rohdin} and Karel {Veselý} and Lukáš {Burget} and Oldřich {Plchot} and Ondřej {Glembek} and Ondřej {Novotný} and Pavel {Matějka}",
  title="BUT Text-Dependent Speaker Verification System for SdSV Challenge 2020",
  booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
  year="2020",
  journal="Proceedings of Interspeech",
  volume="2020",
  number="10",
  pages="761--765",
  publisher="International Speech Communication Association",
  address="Shanghai",
  doi="10.21437/Interspeech.2020-2882",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2020/pdfs/2882.pdf"
}