A conformer-based classifier for variable-length utterance processing in anti-spoofing
Open accessThe DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Abstract
The success achieved by conformers in Automatic Speech Recognition (ASR) leads us to their application in other domains, such as spoofing detection for automatic speaker verification (ASV), where the conformer self-attention mechanism might effectively model and detect the artifacts introduced in spoofed speech signals. Also, conformers can naturally handle the variable duration of speech utterances. However, as with transformers, the conformer performance may degrade when trained with limited data. To address this issue, we propose utilizing conformers in conjunction with self-supervised learning, specifically leveraging a pre-trained model called wav2vec 2.0, which is pre-trained using a substantial amount of bonafide data. Our experimental results demonstrate that our proposed method achieves one of the best results in the recent ASVspoof 2021 logical access (LA) and deep fake (DF) databases.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Conformer [143] (EER increases from 3 . 28% to 94 . 82% on ASVSpoof21)”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [143]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“The transformer architecture leverages self-attention to establish global dependencies between the input and output sequences [13].”
BackgroundSelf-citationExploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 2×
“However, these models require large amounts of training data [16, 17, 18].”
BackgroundAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Conformer: Convolution-augmented Transformer for Speech Recognition
Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-3015 · Cited by 3,150
Conformer: Convolution-augmented Transformer for Speech Recognition
Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.08100 · Cited by 3,150
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Hsu, W.-N., Bolte, B., Tsai, Y.-H. H., Lakhotia, K., Salakhutdinov, R., & Mohamed, A. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3122291 · Cited by 2,983
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
Baevski, A., Zhou, H., Mohamed, A., & Auli, M. (2020) · arXiv · doi:10.48550/arxiv.2006.11477 · Cited by 2,369
fairseq: A Fast, Extensible Toolkit for Sequence Modeling
Ott, M., Edunov, S., Baevski, A., Fan, A., Gross, S., Ng, N., Grangier, D., & Auli, M. (2019) · Proceedings of the 2019 Conference of the North · doi:10.18653/v1/n19-4009 · Cited by 2,344 · cited 1×
“The W2V model was implemented by using the Fairseq project toolkit [34].”
Methodwav2vec: Unsupervised Pre-Training for Speech Recognition
Schneider, S., Baevski, A., Collobert, R., & Auli, M. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1873 · Cited by 1,290
Cited by
XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection
Xiao, Y., & Das, R. K. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3547861 · Cited by 102
“2 demonstrates the inference speed of XLSR-Mamba compared to recent XLSR-Conformer [19], measured using the real-time factor (RTF) on an NVIDIA A5000 GPU, with values averaged over 20 runs.”
InfluentialImproving Short Utterance Anti-Spoofing with Aasist2
Zhang, Y., Lu, J., Shang, Z., Wang, W., & Zhang, P. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448049 · Cited by 64
Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-Spoofing
Liu, T., Truong, D.-T., Das, R. K., Lee, K. A., & Li, H. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3626963 · Cited by 68
“9.17 2024 Conformer [63] 8.42 2024 TCM [33] 7.79 2024 OCKD [70] 7.68 2024 SLS [35] 7.46 (8.87) 2024 Pascu et al. [74] - (7.2) 2025 Mamba [17] 6.71 2025 WaveSpec [72] 6.58 2025 LSR+LSA [71] 5.92 2025 LSR+LSA [71] ※ 5.54 - Proposed Nes2Net 5.80 (7.06) - Proposed Nes2Net-X 5.52 (6.60) ※ : with extra…”
InfluentialAdvancements in AI-Generated Content Forensics: A Systematic Literature Review
Xu, Q., Mu, W., Li, J., Sun, T., & Jiang, X. (2025) · ACM Computing Surveys · doi:10.1145/3760526 · Cited by 26
“More recently, advanced architectures like the Conformer model [185], known for its ability to capture multi-scale features, have been adopted and enhanced with self-attention mechanisms to further boost performance.”
Martín-Doñas, J. M., Álvarez, A., Rosello, E., Gomez, A. M., & Peinado, A. M. (2024) · Interspeech 2024 · doi:10.21437/interspeech.2024-942 · Cited by 18
“…the development of deepfake detectors built upon these SSL architectures, focusing on the following aspects: improving the downstream network [13, 14], using different upstreams such as WavLM [15] or Whisper [16], exploring multi-corpus with domain-invariant training [17], or…”
MethodInfluentialSelf-citation
Metadata
- Authors
- Rosello, E., Gomez-Alanis, A., Gomez, A. M., & Peinado, A.
- Affiliations
- Universidad de Granada (ES)
- Venue
- INTERSPEECH 2023
- Publisher
- ISCA
- Published
- 2023-08-20
- Pages
- 5281-5285
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W4385822395
- Cited by
- 47
- References
- 35
- Citations by year
- 2026: 24 · 2025: 16 · 2024: 6
- FWCI
- 8.14
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- other-oa
- Locations
- Interspeech (USB) (publishedVersion)
- Institutional Repository of the University of Granada (University of Granada) (submittedVersion, other-oa)
- 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
- conformational isomers, anti-spoofing, speaker verification, self-supervised learning, wav2vec 2.0, self-attention, deepfake detection, ASVspoof 2021
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: A conformer-based classifier for variable-length utterance processing in anti-spoofing. https://app.cochat.ai/papers/10.21437/interspeech.2023-1820
- The paper
- Rosello, E., Gomez-Alanis, A., Gomez, A. M., & Peinado, A. (2023). A conformer-based classifier for variable-length utterance processing in anti-spoofing. INTERSPEECH 2023. https://doi.org/10.21437/interspeech.2023-1820
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.