Publication detail

End-to-end DNN based text-independent speaker recognition for long and short utterances

ROHDIN, J. SILNOVA, A. DIEZ SÁNCHEZ, M. PLCHOT, O. MATĚJKA, P. BURGET, L. GLEMBEK, O.

Original Title

End-to-end DNN based text-independent speaker recognition for long and short utterances

Type

journal article in Web of Science

Language

English

Original Abstract

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 present 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 end-to-end systems. The proposed system outperforms the i-vector + PLDA baseline on both long and short duration utterances.

Keywords

Speaker verification, DNN, End-to-end, Text-independent, i-vector, PLDA

Authors

ROHDIN, J.; SILNOVA, A.; DIEZ SÁNCHEZ, M.; PLCHOT, O.; MATĚJKA, P.; BURGET, L.; GLEMBEK, O.

Released

1. 1. 2020

ISBN

0885-2308

Periodical

COMPUTER SPEECH AND LANGUAGE

Year of study

2020

Number

59

State

United Kingdom of Great Britain and Northern Ireland

Pages from

22

Pages to

35

Pages count

14

URL

https://www.sciencedirect.com/science/article/pii/S0885230818303632

BibTex

@article{BUT158088,
  author="Johan Andréas {Rohdin} and Anna {Silnova} and Mireia {Diez Sánchez} and Oldřich {Plchot} and Pavel {Matějka} and Lukáš {Burget} and Ondřej {Glembek}",
  title="End-to-end DNN based text-independent speaker recognition for long and short utterances",
  journal="COMPUTER SPEECH AND LANGUAGE",
  year="2020",
  volume="2020",
  number="59",
  pages="22--35",
  doi="10.1016/j.csl.2019.06.002",
  issn="0885-2308",
  url="https://www.sciencedirect.com/science/article/pii/S0885230818303632"
}

Documents

rohdin_elsevier_Journal_Paper_2020_18303632.pdf