CoChat

HM-CONFORMER: A Conformer-Based Audio Deepfake Detection System with Hierarchical Pooling and Multi-Level Classification Token Aggregation Methods

Open access
Shin, Hyun-seo, Heo, Jungwoo, Kim, Ju-ho, Lim, Chan-yeong, Kim, Wonbin, Yu, Ha-Jin · 2024 · ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

The DOI matches its Crossref record; 25 of the 26 references it cites were found in a registry or an index, and 1 are not checked yet.

Abstract

Audio deepfake detection (ADD) is the task of detecting spoofing attacks generated by text-to-speech or voice conversion systems. Spoofing evidence, which helps to distinguish between spoofed and bona-fide utterances, might exist either locally or globally in the input features. To capture these, the Conformer, which consists of Transformers and CNN, possesses a suitable structure. However, since the Conformer was designed for sequence-to-sequence tasks, its direct application to ADD tasks may be sub-optimal. To tackle this limitation, we propose HM-Conformer by adopting two components: (1) Hierarchical pooling method progressively reducing the sequence length to eliminate duplicated information (2) Multi-level classification token aggregation method utilizing classification tokens to gather information from different blocks. Owing to these components, HM-Conformer can efficiently detect spoofing evidence by processing various sequence lengths and aggregating them. In experimental results on the ASVspoof 2021 Deepfake dataset, HM-Conformer achieved a 15.71% EER, showing competitive performance compared to recent systems.

Overview

Integrity signals

Registry

Crossref · 10.1109/icassp48485.2024.10448453

Cites

25 of 26 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 26 references

Cited by

See all 41

Metadata

Authors
Shin, H.-S., Heo, J., Kim, J.-H., Lim, C.-Y., Kim, W., & Yu, H.-J.
Affiliations
University of Seoul (KR)
Venue
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE
Published
2024-04-14
Pages
10581-10585
ISSN
1520-6149 (ISSN-L)
OpenAlex
W4392903644
Cited by
21
References
24
Citations by year
2026: 7 · 2025: 9 · 2024: 5
FWCI
6.20
Type
conference paper
Language
en
Open access
Locations
  • IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, public-domain)
  • arXiv (Cornell University) (public-domain)
Funders
  • Ministry of Science and ICT, South Korea
  • Institute for Information and Communications Technology Promotion
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 › Music and Audio Processing
Keywords
audio deepfake detection, anti-spoofing, conformational isomers, hierarchical pooling

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: HM-CONFORMER: A Conformer-Based Audio Deepfake Detection System with Hierarchical Pooling and Multi-Level Classification Token Aggregation Methods. https://app.cochat.ai/papers/10.1109/icassp48485.2024.10448453
The paper
Shin, H.-S., Heo, J., Kim, J.-H., Lim, C.-Y., Kim, W., & Yu, H.-J. (2024). HM-CONFORMER: A Conformer-Based Audio Deepfake Detection System with Hierarchical Pooling and Multi-Level Classification Token Aggregation Methods. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp48485.2024.10448453

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.