Publication Details

ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform

PENG Junyi, QU Xiaoyang, WANG Jianzong, GU Rongzhi, XIAO Jing, BURGET Lukáš and ČERNOCKÝ Jan. ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Brno: International Speech Communication Association, 2021, pp. 511-515. ISSN 1990-9772. Available from: https://www.isca-speech.org/archive/interspeech_2021/peng21_interspeech.html
Czech title
ICSpk: Intepretovatelný extraktor komplexních embeddingů mluvčích ze surových signálů
Type
conference paper
Language
english
Authors
Peng Junyi, Msc. Eng. (DCGM FIT BUT)
Qu Xiaoyang (PATS)
Wang Jianzong (PATS)
Gu Rongzhi (PKUSZ)
Xiao Jing (PATS)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
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 - on-line, 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, CZ
DOI
10.21437/Interspeech.2021-2016
UT WoS
000841879500103
EID Scopus
2-s2.0-85119283198
BibTeX 
@INPROCEEDINGS{FITPUB12597,
   author = "Junyi Peng and Xiaoyang Qu and Jianzong Wang and Rongzhi Gu and Jing Xiao and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform",
   pages = "511--515",
   booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
   journal = "Proceedings of Interspeech - on-line",
   volume = 2021,
   number = 8,
   year = 2021,
   location = "Brno, CZ",
   publisher = "International Speech Communication Association",
   ISSN = "1990-9772",
   doi = "10.21437/Interspeech.2021-2016",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12597"
}
Back to top