Detail publikace

On the use of DNN Autoencoder for Robust Speaker Recognition

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

Originální název

On the use of DNN Autoencoder for Robust Speaker Recognition

Anglický název

On the use of DNN Autoencoder for Robust Speaker Recognition

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

Dokumenty

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",
  annote="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.",
  address="Faculty of Information Technology BUT",
  chapter="161935",
  edition="NEUVEDEN",
  howpublished="print",
  institution="Faculty of Information Technology BUT",
  year="2018",
  month="november",
  pages="1--5",
  publisher="Faculty of Information Technology BUT",
  type="report"
}