Publication detail

On the use of DNN Autoencoder for Robust Speaker Recognition

NOVOTNÝ, O. MATĚJKA, P. PLCHOT, O. GLEMBEK, O.

Original Title

On the use of DNN Autoencoder for Robust Speaker Recognition

Type

report

Language

English

Original Abstract

In this paper, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. The target application is a robust speaker recognition system. We started with augmenting the Fisher database with artificially noised and reverberated data and we trained the autoencoder to map noisy and reverberated speech to its clean version. We use the autoencoder as a preprocessing step for a stateof- the-art text-independent speaker recognition system. We compare results achieved with pure autoencoder enhancement, multi-condition PLDA training and their simultaneous use. We present a detailed analysis with various conditions of NIST SRE 2010, PRISM and artificially corrupted NIST SRE 2010 telephone condition. We conclude that the proposed preprocessing significantly outperforms the baseline and that this technique can be used to build a robust speaker recognition system for reverberated and noisy data.

Keywords

speaker recognition, signal enhancement, autoencoder

Authors

NOVOTNÝ, O.; MATĚJKA, P.; PLCHOT, O.; GLEMBEK, O.

Released

8. 11. 2018

Publisher

Faculty of Information Technology BUT

Location

Brno

Pages from

1

Pages to

5

Pages count

5

URL

https://www.fit.vut.cz/research/publication/11855/

BibTex

@techreport{BUT161935,
  author="Ondřej {Novotný} and Pavel {Matějka} and Oldřich {Plchot} and Ondřej {Glembek}",
  title="On the use of DNN Autoencoder for Robust Speaker Recognition",
  year="2018",
  publisher="Faculty of Information Technology BUT",
  address="Brno",
  pages="1--5",
  url="https://www.fit.vut.cz/research/publication/11855/"
}