Publication Details
Multi-Channel Speaker Verification with Conv-Tasnet Based Beamformer
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Conv-TasNet, beamforming, embedding extractor, speaker verification, MultiSV
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.
@INPROCEEDINGS{FITPUB12786, author = "Ladislav Mo\v{s}ner and Old\v{r}ich Plchot and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}", title = "Multi-Channel Speaker Verification with Conv-Tasnet Based Beamformer", pages = "7982--7986", booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings", year = 2022, location = "Singapore, SG", publisher = "IEEE Signal Processing Society", ISBN = "978-1-6654-0540-9", doi = "10.1109/ICASSP43922.2022.9747771", language = "english", url = "https://www.fit.vut.cz/research/publication/12786" }