CoChat

Fake Audio Detection Based On Unsupervised Pretraining Models

Lv, Zhiqiang, Zhang, Shanshan, Tang, Kai, Hu, Pengfei · 2022 · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Cited by 56

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Abstract

This work presents our systems for the ADD2022 challenge. The ADD2022 challenge is the first audio deep synthesis detection challenge, which aims to spot various kinds of fake audios. We have explored using unsupervised pretraining models to build fake audio detection systems. Results indicate that unsupervised pretraining models can achieve excellent performance for fake audio detection. Our final EER results for low-quality fake audio detection and partially fake audio detection are 32.80% and 4.80% relatively. For partially fake audio detection, our results ranked first in the competition. Even trained with totally mismatched data, our method still generalizes well for partially fake audio detection.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1109/icassp43922.2022.9747605

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Self-check

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

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

Citations

Cites

Show all 15 references

Research works printed but not linked: 16

  1. 10.21437/Interspeech.2021-807 · DOI
  2. 10.1109/TASLP.2019.2946897 · DOI
  3. 10.1109/TIFS.2019.2956589 · DOI · Paper page
  4. 10.1016/j.dsp.2019.102622 · DOI · Paper page
  5. 10.1109/ASRU46091.2019.9003845 · DOI · Paper page
  6. 10.21437/ASVSPOOF.2021-4 · DOI · Paper page
  7. 10.21437/ASVSPOOF.2021-13 · DOI
  8. kang, 2021, CRIM’s System Description for the ASVSpoof2021 Challenge, Proc ASVspoof 2021 Workshop, 100
  9. 10.21437/Odyssey.2016-39 · DOI
  10. 10.21437/Odyssey.2018-55 · doi:10.21437/odyssey.2018-55
  11. 10.21437/Odyssey.2016-41 · DOI · Paper page
  12. 10.21437/Interspeech.2021-930 · DOI · Paper page
  13. 10.1109/ACCESS.2019.2917470 · DOI
  14. 10.1109/ICASSP.2018.8461375 · DOI · Paper page
  15. baevski, 2020, wav2vec 2.0: A framework for self-supervised learning of speech representations, ArXiv
  16. 10.1109/CVPR.2018.00745 · DOI · Paper page

Cited by

See all 56

Metadata

Authors
Lv, Z., Zhang, S., Tang, K., & Hu, P.
Venue
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE
Published
2022-05-23
Pages
9231-9235
ISSN
1520-6149 (ISSN-L)
OpenAlex
W4224932929
Cited by
56
References
15
FWCI
7.64
Type
conference paper
Language
en
Open access
closed

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Fake Audio Detection Based On Unsupervised Pretraining Models. https://app.cochat.ai/papers/10.1109/icassp43922.2022.9747605
The paper
Lv, Z., Zhang, S., Tang, K., & Hu, P. (2022). Fake Audio Detection Based On Unsupervised Pretraining Models. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp43922.2022.9747605

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.