Detail publikace

ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform

PENG, J. QU, X. WANG, J. GU, R. XIAO, J. BURGET, L. ČERNOCKÝ, J.

Originální název

ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Recently, extracting speaker embedding directly from raw waveformhas drawn increasing attention in the field of speaker verification.Parametric real-valued filters in the first convolutionallayer are learned to transform the waveform into time-frequencyrepresentations. However, these methods only focus on themagnitude spectrum and the poor interpretability of the learnedfilters limits the performance. In this paper, we propose a complexspeaker embedding extractor, named ICSpk, with higherinterpretability and fewer parameters. Specifically, at first, toquantify the speaker-related frequency response of waveform,we modify the original short-term Fourier transform filters intoa family of complex exponential filters, named interpretablecomplex (IC) filters. Each IC filter is confined by a complexexponential filter parameterized by frequency. Then, a deepcomplex-valued speaker embedding extractor is designed to operateon the complex-valued output of IC filters. The proposedICSpk is evaluated onVoxCeleb andCNCeleb databases. Experimentalresults demonstrate the IC filters-based system exhibitsa significant improvement over the complex spectrogram basedsystems. Furthermore, the proposed ICSpk outperforms existingraw waveform based systems by a large margin.

Klíčová slova

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

Autoři

PENG, J.; QU, X.; WANG, J.; GU, R.; XIAO, J.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

30. 8. 2021

Nakladatel

International Speech Communication Association

Místo

Brno

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2021

Číslo

8

Stát

Francouzská republika

Strany od

511

Strany do

515

Strany počet

5

URL

https://www.isca-speech.org/archive/interspeech_2021/peng21_interspeech.html

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"
}

Dokumenty

peng21_interspeech.pdf