Skip to main content

Robust audio anti-spoofing countermeasure with joint training of front-end and back-end models

Publication ,  Conference
Wang, X; Zeng, B; Suo, H; Wan, Y; Li, M
Published in: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
January 1, 2023

The accuracy and reliability of many speech processing systems may deteriorate under noisy conditions. This paper discusses robust audio anti-spoofing countermeasure for audio in noisy environments. Firstly, we attempt to use a pre-trained speech enhancement model as the front-end module and build a cascaded system. However, the independent denoising process of enhancement models may distort the synthesis artifacts or anti-spoofing related information included in utterances, leading to performance degradation. Therefore, we proposes a new framework for robust audio anti-spoofing by joint training the integrated speech enhancement front-end and anti-spoofing back-end. The final results demonstrate that the joint training framework is more effective than the cascaded framework. Additionally, we propose a cross-joint training scheme, which allows the single-model performance to exceed the result of score level fusion, making the joint framework more effective and efficient.

Duke Scholars

Published In

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

DOI

EISSN

1990-9772

ISSN

2308-457X

Publication Date

January 1, 2023

Volume

2023-August

Start / End Page

4004 / 4008
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, X., Zeng, B., Suo, H., Wan, Y., & Li, M. (2023). Robust audio anti-spoofing countermeasure with joint training of front-end and back-end models. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (Vol. 2023-August, pp. 4004–4008). https://doi.org/10.21437/Interspeech.2023-1166
Wang, X., B. Zeng, H. Suo, Y. Wan, and M. Li. “Robust audio anti-spoofing countermeasure with joint training of front-end and back-end models.” In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2023-August:4004–8, 2023. https://doi.org/10.21437/Interspeech.2023-1166.
Wang X, Zeng B, Suo H, Wan Y, Li M. Robust audio anti-spoofing countermeasure with joint training of front-end and back-end models. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2023. p. 4004–8.
Wang, X., et al. “Robust audio anti-spoofing countermeasure with joint training of front-end and back-end models.” Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2023-August, 2023, pp. 4004–08. Scopus, doi:10.21437/Interspeech.2023-1166.
Wang X, Zeng B, Suo H, Wan Y, Li M. Robust audio anti-spoofing countermeasure with joint training of front-end and back-end models. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2023. p. 4004–4008.

Published In

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

DOI

EISSN

1990-9772

ISSN

2308-457X

Publication Date

January 1, 2023

Volume

2023-August

Start / End Page

4004 / 4008