Publication Details
Learnable Sparse Filterbank for Speaker Verification
GU, R.
Mošner Ladislav, Ing. (DCGM)
Plchot Oldřich, Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
learnable filter, sparse filtering, sparsity, speaker verification
Recently, feature extraction with learnable filters was extensively
investigated with speaker verification systems, with filters
learned both in time- and frequency-domains. Most of the
learned schemes however end up with filters close to their initialization
(e.g. Mel filterbank) or filters strongly limited by
their constraints. In this paper, we propose a novel learnable
sparse filterbank, named LearnSF, by exclusively optimizing
the sparsity of the filterbank, that does not explicitly constrain
the filters to follow pre-defined distribution. After standard
pre-processing (STFT and square of the magnitude spectrum),
the learnable sparse filterbank is employed, with its normalized
outputs fed into a neural network predicting the speaker identity.
We evaluated the performance of the proposed approach
on both VoxCeleb and CNCeleb datasets. The experimental
results demonstrate the effectiveness of the proposed LearnSF
compared to both widely-used acoustic features and existing parameterized
learnable front-ends.
@inproceedings{BUT179826,
author="PENG, J. and GU, R. and MOŠNER, L. and PLCHOT, O. and BURGET, L. and ČERNOCKÝ, J.",
title="Learnable Sparse Filterbank for Speaker Verification",
booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
year="2022",
journal="Proceedings of Interspeech",
number="9",
pages="5110--5114",
publisher="International Speech Communication Association",
address="Incheon",
doi="10.21437/Interspeech.2022-11309",
issn="1990-9772",
url="https://www.isca-speech.org/archive/pdfs/interspeech_2022/peng22e_interspeech.pdf"
}