CoChat

Replay and Synthetic Speech Detection with Res2Net Architecture

Li, Xu, Li, Na, Weng, Chao, Liu, Xunying, Su, Dan, Yu, Dong, Meng, Helen · 2021 · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.

Abstract

Existing approaches for replay and synthetic speech detection still lack generalizability to unseen spoofing attacks. This work proposes to leverage a novel model structure, so-called Res2Net, to improve the anti-spoofing countermeasure’s generalizability. Res2Net mainly modifies the ResNet block to enable multiple feature scales. Specifically, it splits the feature maps within one block into multiple channel groups and designs a residual-like connection across different channel groups. Such connection increases the possible receptive fields, resulting in multiple feature scales. This multiple scaling mechanism significantly improves the countermeasure’s generalizability to unseen spoofing attacks. It also decreases the model size compared to ResNet-based models. Experimental results show that the Res2Net model consistently outperforms ResNet34 and ResNet50 by a large margin in both physical access (PA) and logical access (LA) of the ASVspoof 2019 corpus. Moreover, integration with the squeeze-and-excitation (SE) block can further enhance performance. For feature engineering, we investigate the gen-eralizability of Res2Net combined with different acoustic features, and observe that the constant-Q transform (CQT) achieves the most promising performance in both PA and LA scenarios. Our best single system outperforms other state-of-the-art single systems in both PA and LA of the ASVspoof 2019 corpus.

Overview

Integrity signals

Registry

Crossref · 10.1109/icassp39728.2021.9413828

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Citations

Cites

Show all 30 references

Cited by

See all 197

Metadata

Authors
Li, X., Li, N., Weng, C., Liu, X., Su, D., Yu, D., & Meng, H.
Affiliations
  • Chinese University of Hong Kong (HK)
  • Tencent (China) (CN)
Venue
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
IEEE
Published
2021-06-06
Pages
6354-6358
ISSN
1520-6149 (ISSN-L)
OpenAlex
W3161011913
Cited by
186
References
28
Citations by year
2026: 11 · 2025: 43 · 2024: 44 · 2023: 42 · 2022: 29 · 2021: 17
FWCI
15.12
Type
conference paper
Language
en
Open access
closed
Locations
IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
Keywords
replay attack detection, synthetic speech detection, anti-spoofing, Res2Net, squeeze-and-excitation, constant-Q transform, acoustic features, speaker verification

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: Replay and Synthetic Speech Detection with Res2Net Architecture. https://app.cochat.ai/papers/10.1109/icassp39728.2021.9413828
The paper
Li, X., Li, N., Weng, C., Liu, X., Su, D., Yu, D., & Meng, H. (2021). Replay and Synthetic Speech Detection with Res2Net Architecture. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp39728.2021.9413828

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.