CoChat
Sign Up
Cited by 61Speech Recognition and SynthesisSpeech and Audio ProcessingBiometric Identification and Security

UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021

Open access
Chen, Xinhui, Zhang, You, Zhu, Ge, Duan, Zhiyao·2021·2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge
DOI 10.21437/asvspoof.2021-12
Open this paper in CoChat — free accountOpen PDF

Abstract

In this paper, we present UR-AIR system submission to the logical access (LA) and the speech deepfake (DF) tracks of the ASVspoof 2021 Challenge. The LA and DF tasks focus on synthetic speech detection (SSD), i.e. detecting text-to-speech and voice conversion as spoofing attacks. Different from previous ASVspoof challenges, the LA task this year presents codec and transmission channel variability, while the new task DF presents general audio compression. Built upon our previous research work on improving the robustness of the SSD systems to channel effects, we propose a channel-robust synthetic speech detection system for the challenge. To mitigate the channel variability issue, we use an acoustic simulator to apply transmission codec, compression codec, and convolutional impulse responses to augmenting the original datasets. For the neural network backbone, we propose to use Emphasized Channel Attention, Propagation and Aggregation Time Delay Neural Networks (ECAPA-TDNN) as our primary model. We also incorporate one-class learning with channel-robust training strategies to further learn a channel-invariant speech representation. Our submission achieved EER 20.33% in the DF task; EER 5.46% and min-tDCF 0.3094 in the LA task.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21437/asvspoof.2021-12

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Methods based on self-supervised representations provide a lighter and more robust alternative compared to previous generation approaches such as ResNet on LFCC or RawNet.

    “This is also the case for our task of interest, audio deepfake detection, where methods based on self-supervised representations provide a lighter [7] and more robust [8] alternative compared to the previous generation of approaches, such as ResNet on linear frequency cepstral coefficients (LFCC) [14] or RawNet [15].”

    From WavLM model ensemble for audio deepfake detection (2024) · cites this paper as [14]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 30

  1. Judith A Markowitz, "Voice biometrics," Communica- tions of the ACM, vol. 43, no. 9, pp. 66-73, 2000.
  2. John HL Hansen and Taufiq Hasan, "Speaker recognition by machines and humans: A tutorial review," IEEE Signal Processing Magazine, vol. 32, no. 6, pp. 74-99, 2015.
  3. Zhizheng Wu, Nicholas Evans, Tomi Kinnunen, Junichi Yamagishi, Federico Alegre, and Haizhou Li, "Spoofing and countermeasures for speaker verification: A survey," Speech Communication, vol. 66, pp. 130-153, 2015.
  4. Zhizheng Wu, Phillip L. De Leon, Cenk Demiroglu, Ali Khodabakhsh, Simon King, Zhen-Hua Ling, Daisuke Saito, Bryan Stewart, Tomoki Toda, Mirjam Wester, and Junichi Yamagishi, "Anti-spoofing for text-independent speaker verification: An initial database, comparison of countermeasures, and human performance," IEEE/ACM Transactions on Audio, Speech, and Language Process- ing, vol. 24, no. 4, pp. 768-783, 2016.
  5. Madhu R Kamble, Hardik B Sailor, Hemant A Patil, and Haizhou Li, "Advances in anti-spoofing: from the per- spective of ASVspoof challenges," APSIPA Transactions on Signal and Information Processing, vol. 9, 2020.
  6. Joao Monteiro, Jahangir Alam, and Tiago H Falk, "Gen- eralized end-to-end detection of spoofing attacks to au- tomatic speaker recognizers," Computer Speech & Lan- guage, vol. 63, pp. 101096, 2020.
  7. You Zhang, Fei Jiang, and Zhiyao Duan, "One-class learn- ing towards synthetic voice spoofing detection," IEEE Sig- nal Processing Letters, vol. 28, pp. 937-941, 2021.
  8. Xin Wang and Junich Yamagishi, "A comparative study on recent neural spoofing countermeasures for synthetic speech detection," Proc. Interspeech, 2021.
  9. Tianxiang Chen, Avrosh Kumar, Parav Nagarsheth, Ganesh Sivaraman, and Elie Khoury, "Generalization of audio deepfake detection," in Proc. Odyssey, 2020, pp. 132-137.
  10. João Monteiro, Jahangir Alam, and Tiago H Falk, "An en- semble based approach for generalized detection of spoof- ing attacks to automatic speaker recognizers," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 6599-6603.
  11. Rohan Kumar Das, Jichen Yang, and Haizhou Li, "As- sessing the scope of generalized countermeasures for anti- spoofing," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 6589-6593.
  12. Rohan Kumar Das, Tomi Kinnunen, Wen-Chin Huang, Zhen-Hua Ling, Junichi Yamagishi, Zhao Yi, Xiaohai Tian, and Tomoki Toda, "Predictions of subjective ratings and spoofing assessments of voice conversion challenge 2020 submissions," in Proc. Joint Workshop for the Bliz- zard Challenge and Voice Conversion Challenge, 2020, pp. 99-120.
  13. Cemal Hanilci, Tomi Kinnunen, Md Sahidullah, and Aleksandr Sizov, "Spoofing detection goes noisy: An analysis of synthetic speech detection in the presence of additive noise," Speech Communication, vol. 85, pp. 83- 97, 2016.
  14. You Zhang, Ge Zhu, Fei Jiang, and Zhiyao Duan, "An em- pirical study on channel effects for synthetic voice spoof- ing countermeasure systems," Proc. Interspeech, 2021.
  15. Brecht Desplanques, Jenthe Thienpondt, and Kris De- muynck, "ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in tdnn based speaker verifi- cation," Proc. Interspeech, pp. 3830-3834, 2020.
  16. Marc Ferras, Srikanth Madikeri, Petr Motlicek, Sub- hadeep Dey, and Hervé Bourlard, "A large-scale open- source acoustic simulator for speaker recognition," IEEE Signal Processing Letters, vol. 23, no. 4, pp. 527-531, 2016.
  17. Alex Waibel, Toshiyuki Hanazawa, Geoffrey Hinton, Kiy- ohiro Shikano, and Kevin J Lang, "Phoneme recognition using time-delay neural networks," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 37, no. 3, pp. 328-339, 1989.
  18. Vijayaditya Peddinti, Daniel Povey, and Sanjeev Khudan- pur, "A time delay neural network architecture for effi- cient modeling of long temporal contexts," in Proc. Inter- speech, 2015.
  19. Kyu J Han, Jing Pan, Venkata Krishna Naveen Tadala, Tao Ma, and Dan Povey, "Multistream cnn for robust acoustic modeling," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 6873-6877.
  20. David Snyder, Daniel Garcia-Romero, Gregory Sell, Daniel Povey, and Sanjeev Khudanpur, "X-vectors: Ro- bust dnn embeddings for speaker recognition," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, pp. 5329-5333.
  21. Hossein Zeinali, Lukáš Burget, Johan Rohdin, The- mos Stafylakis, and Jan Cernocky, "How to improve your speaker embeddings extractor in generic toolkits," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 6141- 6145.
  22. Xu Li, Na Li, Chao Weng, Xunying Liu, Dan Su, Dong Yu, and Helen Meng, "Replay and synthetic speech de- tection with res2net architecture," in Proc. IEEE Interna- tional Conference on Acoustics, Speech and Signal Pro- cessing (ICASSP), 2021, pp. 6354-6358.
  23. Arsha Nagrani, Joon Son Chung, Jaesung Huh, Andrew Brown, Ernesto Coto, Weidi Xie, Mitchell McLaren, Douglas A Reynolds, and Andrew Zisserman, "Voxsrc 2020: The second voxceleb speaker recognition chal- lenge," arXiv preprint arXiv:2012.06867, 2020. · arXiv
  24. Hossein Zeinali, Kong Aik Lee, Jahangir Alam, and Lukas Burget, "SdSV challenge 2020: Large-scale evaluation of short-duration speaker verification.," in Proc. Interspeech, 2020, pp. 731-735.
  25. Niko Brümmer and Edward De Villiers, "The bosaris toolkit: Theory, algorithms and code for surviving the new dcf," arXiv preprint arXiv:1304.2865, 2013. · arXiv
  26. Tomi Kinnunen, Héctor Delgado, Nicholas Evans, Kong Aik Lee, Ville Vestman, Andreas Nautsch, Massim- iliano Todisco, Xin Wang, Md Sahidullah, Junichi Yamag- ishi, et al., "Tandem assessment of spoofing countermea- sures and automatic speaker verification: Fundamentals," IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 2195-2210, 2020.
  27. Rajeev Ranjan, Carlos D Castillo, and Rama Chellappa, "L2-constrained softmax loss for discriminative face veri- fication," arXiv preprint arXiv:1703.09507, 2017. · arXiv
  28. Hossein Zeinali, Themos Stafylakis, Georgia Athana- sopoulou, Johan Rohdin, Ioannis Gkinis, Lukas Burget, and Jan Cernocky, "Detecting spoofing attacks using vgg and sincnet: BUT-Omilia submission to ASVspoof 2019 challenge," Proc. Interspeech, pp. 1073-1077, 2019.
  29. Massimiliano Todisco, Héctor Delgado, and Nicholas WD Evans, "A new feature for automatic speaker verification anti-spoofing: Constant q cepstral coefficients.," in Proc. Odyssey, 2016, vol. 2016, pp. 283-290.
  30. Hemlata Tak, Jose Patino, Massimiliano Todisco, Andreas Nautsch, Nicholas Evans, and Anthony Larcher, "End- to-end anti-spoofing with RawNet2," in Proc. IEEE In- ternational Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 6369-6373.

Cited by

Sorted by citations

Authors
Chen, X., Zhang, Y., Zhu, G., & Duan, Z.
Affiliations
University of Rochester (US)
Corresponding author
Zhang, You
ORCID
Venue
2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge
Publisher
ISCA
Published
2021-09-16
Pages
75-82
DOI
10.21437/asvspoof.2021-12
OpenAlex
W3199131409
Cited by
61
References
5
Citations by year
2026: 12 · 2025: 14 · 2024: 10 · 2023: 13 · 2022: 12
FWCI
4.04
Type
conference paper
Language
en
Open access
Locations
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
National Science Foundation (1922591, 1741472)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
  • Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
Keywords
synthetic speech detection, anti-spoofing, ASVspoof 2021, speech deepfake detection, channel robustness, audio compression, acoustic simulation, data augmentation, ECAPA-TDNN, one-class learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review