Přístupnostní navigace
E-application
Search Search Close
Publication detail
MOŠNER, L. PLCHOT, O. BURGET, L. ČERNOCKÝ, J.
Original Title
Multi-Channel Speaker Verification with Conv-Tasnet Based Beamformer
Type
conference paper
Language
English
Original Abstract
We focus on the problem of speaker recognition in far-field multichannel data. The main contribution is introducing an alternative way of predicting spatial covariance matrices (SCMs) for a beamformer from the time domain signal. We propose to use ConvTasNet, a well-known source separation model, and we adapt it to perform speech enhancement by forcing it to separate speech and additive noise. We experiment with using the STFT of Conv-TasNet outputs to obtain SCMs of speech and noise, and finally, we fine-tune this multi-channel frontend w.r.t. speaker verification objective. We successfully tackle the problem of the lack of a realistic multichannel training set by using simulated data of MultiSV corpus. The analysis is performed on its retransmitted and simulated test parts. We achieve consistent improvements with a 2.7 times smaller model than the baseline based on a scheme with mask estimating NN.
Keywords
Conv-TasNet, beamforming, embedding extractor, speaker verification, MultiSV
Authors
MOŠNER, L.; PLCHOT, O.; BURGET, L.; ČERNOCKÝ, J.
Released
27. 5. 2022
Publisher
IEEE Signal Processing Society
Location
Singapore
ISBN
978-1-6654-0540-9
Book
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages from
7982
Pages to
7986
Pages count
5
URL
https://ieeexplore.ieee.org/document/9747771
BibTex
@inproceedings{BUT178381, author="Ladislav {Mošner} and Oldřich {Plchot} and Lukáš {Burget} and Jan {Černocký}", title="Multi-Channel Speaker Verification with Conv-Tasnet Based Beamformer", booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings", year="2022", pages="7982--7986", publisher="IEEE Signal Processing Society", address="Singapore", doi="10.1109/ICASSP43922.2022.9747771", isbn="978-1-6654-0540-9", url="https://ieeexplore.ieee.org/document/9747771" }