Publication Details

ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform

PENG, J.; QU, X.; WANG, J.; GU, R.; XIAO, J.; BURGET, L.; ČERNOCKÝ, J. ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Proceedings of Interspeech. Brno: International Speech Communication Association, 2021. p. 511-515. ISSN: 1990-9772.
Czech title
ICSpk: Intepretovatelný extraktor komplexních embeddingů mluvčích ze surových signálů
Type
conference paper
Language
English
Authors
Peng Junyi (DCGM)
QU, X.
WANG, J.
GU, R.
XIAO, J.
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
URL
Keywords

end-to-end speaker verification, raw waveform, complex neural networks,
interpretable complex filters

Abstract

Recently, extracting speaker embedding directly from raw waveform has drawn
increasing attention in the field of speaker verification. Parametric real-valued
filters in the first convolutional layer are learned to transform the waveform
into time-frequency representations. However, these methods only focus on the
magnitude spectrum and the poor interpretability of the learned filters limits
the performance. In this paper, we propose a complex speaker embedding extractor,
named ICSpk, with higher interpretability and fewer parameters. Specifically, at
first, to quantify the speaker-related frequency response of waveform, we modify
the original short-term Fourier transform filters into a family of complex
exponential filters, named interpretable complex (IC) filters. Each IC filter is
confined by a complex exponential filter parameterized by frequency. Then, a deep
complex-valued speaker embedding extractor is designed to operate on the
complex-valued output of IC filters. The proposed ICSpk is evaluated onVoxCeleb
andCNCeleb databases. Experimental results demonstrate the IC filters-based
system exhibits a significant improvement over the complex spectrogram based
systems. Furthermore, the proposed ICSpk outperforms existing raw waveform based
systems by a large margin.

Published
2021
Pages
511–515
Journal
Proceedings of Interspeech, vol. 2021, no. 8, ISSN 1990-9772
Proceedings
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Conference
Interspeech Conference, Brno, CZ
Publisher
International Speech Communication Association
Place
Brno
DOI
UT WoS
000841879500103
EID Scopus
BibTeX
@inproceedings{BUT175835,
  author="PENG, J. and QU, X. and WANG, J. and GU, R. and XIAO, J. and BURGET, L. and ČERNOCKÝ, J.",
  title="ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform",
  booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
  year="2021",
  journal="Proceedings of Interspeech",
  volume="2021",
  number="8",
  pages="511--515",
  publisher="International Speech Communication Association",
  address="Brno",
  doi="10.21437/Interspeech.2021-2016",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/interspeech_2021/peng21_interspeech.html"
}
Files
Back to top