Publication detail

Effective Phase Encoding for End-To-End Speaker Verification

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

Original Title

Effective Phase Encoding for End-To-End Speaker Verification

Type

conference paper

Language

English

Original Abstract

The widely used magnitude spectrum based features have shown their superiority in the field of speech processing. In contrast, the importance of phase spectrum is always ignored. This is because the patterns hidden in phase cannot be intuitively modelled and interpreted, due to phase wrapping phenomenon. In this paper, we explore novel phase spectrum based features, named Learnable Group Delay (LearnGD), to capture useful information in speech signals. Specifically, firstly, the negative of the spectral derivative of the phase spectrum, called group delay (GD), is used to unwrap the phase. Then, to suppress the spiky nature of GD, which is caused by its roots close to the unit circle in the Z domain, a carefully designed light convolutional smoothing layer is employed to reconstruct the GD. Finally, an exponential hyper-parameter is introduced to reconstruct GD features to restore the spectrum range and generate LearnGD features. For performance evaluation, speaker verification experiments are conducted on the VoxCeleb2 corpus. Compared to the traditional acoustic feature derived from the magnitude spectrum, the proposed phase-based features reach a 27.8% relative improvement in terms of EER. Furthermore, experimental results on TIMIT phoneme recognition task also demonstrate the effectiveness of our proposed phase-based features.

Keywords

end-to-end speaker verification, phase information, group delay, on-the-fly

Authors

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

Released

30. 8. 2021

Publisher

International Speech Communication Association

Location

Brno

ISBN

1990-9772

Periodical

Proceedings of Interspeech

Year of study

2021

Number

8

State

French Republic

Pages from

2366

Pages to

2370

Pages count

5

URL

BibTex

@inproceedings{BUT175842,
  author="PENG, J. and QU, X. and GU, R. and WANG, J. and XIAO, J. and BURGET, L. and ČERNOCKÝ, J.",
  title="Effective Phase Encoding for End-To-End Speaker Verification",
  booktitle="Proceedings Interspeech 2021",
  year="2021",
  journal="Proceedings of Interspeech",
  volume="2021",
  number="8",
  pages="2366--2370",
  publisher="International Speech Communication Association",
  address="Brno",
  doi="10.21437/Interspeech.2021-2025",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/interspeech_2021/peng21c_interspeech.html"
}