Dereverberation and Beamforming in Far-Field Speaker Recognition

Ladislav Mosner; Pavel Matejka; Ondrej Novotný; Jan Honza Cernocký

ICASSP 2018accepted0 citations

Dereverberation and Beamforming in Far-Field Speaker Recognition

Ladislav Mosner, Pavel Matejka, Ondrej Novotný, Jan Honza Cernocký

Abstract

This paper deals with far-field speaker recognition. On a corpus of NIST SRE 2010 data retransmitted in a real room with multiple microphones, we first demonstrate how room acoustics cause significant degradation of state-of-the-art i-vector based speaker recognition system. We then investigate several techniques to improve the performances ranging from probabilistic linear discriminant analysis (PLDA) re-training, through dereverberation, to beamforming. We found that weighted prediction error (WPE) based dereverberation combined with generalized eigenvalue beamformer with power-spectral density (PSD) weighting masks generated by neural networks (NN) provides results approaching the clean close-microphone setup. Further improvement was obtained by re-training PLDA or the mask-generating NNs on simulated target data. The work shows that a speaker recognition system working robustly in the far-field scenario can be developed.

BibTeX

@inproceedings{icassp2018_dereverberationa,
  title = {Dereverberation and Beamforming in Far-Field Speaker Recognition},
  author = {Ladislav Mosner and Pavel Matejka and Ondrej Novotný and Jan Honza Cernocký},
  booktitle = {ICASSP 2018},
  year = {2018}
}