Faculty of Information Technology, BUT

Publication Details

Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition

NOVOTNÝ Ondřej, PLCHOT Oldřich, GLEMBEK Ondřej, ČERNOCKÝ Jan and BURGET Lukáš. Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition. Computer Speech and Language, vol. 2019, no. 58, pp. 403-421. ISSN 0885-2308. Available from: https://www.sciencedirect.com/science/article/pii/S0885230818303607
Czech title
Analýza čištění signálu pomocí DNN pro robustní rozpoznávání mluvčího
Type
journal article
Language
english
Authors
Novotný Ondřej, Ing. (DCGM FIT BUT)
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, doc. Dr. Ing. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords
Speakerverification; Signalenhancement; Autoencoder; Neuralnetwork; Robustness; Embedding
Abstract
In this work, we present an analysis of a DNN-based autoencoder for speech enhancement, dereverberation and denoising. Thetarget application is a robust speaker verification (SV) system. We start our approach by carefully designing a data augmentationprocess to cover a wide range of acoustic conditions and to obtain rich training data for various components of our SV system.We augment several well-known databases used in SV with artificially noised and reverberated data and we use them to train adenoising autoencoder (mapping noisy and reverberated speech to its clean version) as well as an x-vector extractor which is cur-rently considered as state-of-the-art in SV. Later, we use the autoencoder as a preprocessing step for a text-independent SV sys-tem. We compare results achieved with autoencoder enhancement, multi-condition PLDA training and their simultaneous use.We present a detailed analysis with various conditions of NIST SRE 2010, 2016, PRISM and with re-transmitted data. We con-clude that the proposed preprocessing can significantly improve both i-vector and x-vector baselines and that this technique canbe used to build a robust SV system for various target domains.
Published
2019
Pages
403-421
Journal
Computer Speech and Language, vol. 2019, no. 58, ISSN 0885-2308
Publisher
Elsevier Science
DOI
10.1016/j.csl.2019.06.004
BibTeX 
@ARTICLE{FITPUB12039,
   author = "Ond\v{r}ej Novotn\'{y} and Old\v{r}ich Plchot and Ond\v{r}ej Glembek and Jan \v{C}ernock\'{y} and Luk\'{a}\v{s} Burget",
   title = "Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition",
   pages = "403--421",
   journal = "Computer Speech and Language",
   volume = 2019,
   number = 58,
   year = 2019,
   ISSN = "0885-2308",
   doi = "10.1016/j.csl.2019.06.004",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12039"
}
Back to top