The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Towards End-to-End Synthetic Speech Detection
Open accessAbstract
The constant Q transform (CQT) has been shown to be one of the most effective speech signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted (subband) constant Q cepstral coefficient (CQCC) feature extraction and a back-end binary classifier, or a deep neural network (DNN) directly for further feature extraction and classification. Despite the rich literature on such a pipeline, we show in this paper that the pre-transform and hand-crafted features could simply be replaced by end-to-end DNNs. Specifically, we experimentally verify that by only using standard components, a light-weight neural network could outperform the state-of-the-art methods for the ASVspoof2019 challenge. The proposed model is termed Time-domain Synthetic Speech Detection Net (TSSDNet), having ResNet- or Inception-style structures. We further demonstrate that the proposed models also have attractive generalization capability. Trained on ASVspoof2019, they could achieve promising detection performance when tested on disjoint ASVspoof2015, significantly better than the existing cross-dataset results. This paper reveals the great potential of end-to-end DNNs for synthetic speech detection, without hand-crafted features.
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.
Integrity signals
Registry
Cites
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.
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
Multi-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738 · cited 1×
“Noticeably, to increase the receptive field and control model complexity, dilated convolutions [39] with dilation d are incorporated in the IncTSSDNet, which is different from the original Inception network [36].”
MethodASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T., & Lee, K. A. (2019) · arXiv · doi:10.48550/arxiv.1904.05441 · Cited by 688 · cited 2×
“Method 2019 2015 Eval Dev Eval Baseline LFCC+GMM [42] 9.”
MethodASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T. H., & Lee, K. A. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2249 · Cited by 687
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech
Wang, X., Yamagishi, J., Todisco, M., Delgado, H., Nautsch, A., Evans, N., Sahidullah, M., Vestman, V., Kinnunen, T., Lee, K. A., et al. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101114 · Cited by 505 · cited 2×
“We demonstrate that via proper training, the proposed networks outperform the state-of-the-art hand-crafted feature based detectors as well as DNN based ones on the challenging ASVspoof2019 dataset [31].”
BackgroundEnd-to-End anti-spoofing with RawNet2
Tak, H., Patino, J., Todisco, M., Nautsch, A., Evans, N., & Larcher, A. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9414234 · Cited by 402 · cited 2×
“, the RawNet2 [46] is used as a baseline.”
MethodA comparison of features for synthetic speech detection
Sahidullah, M., Kinnunen, T., & Hanilçi, C. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-472 · Cited by 382
Replay and Synthetic Speech Detection with Res2Net Architecture
Li, X., Li, N., Weng, C., Liu, X., Su, D., Yu, D., & Meng, H. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9413828 · Cited by 186 · cited 10×
“For example, the CQT feature, more precisely the log power spectrum of the CQT [30], does not have the phase information of the signal.”
BackgroundMethodInfluentialLong Range Acoustic Features for Spoofed Speech Detection
Das, R. K., Yang, J., & Li, H. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1887 · Cited by 53 · cited 2×
“We make the following remarks from the main results. i) The of [19] and [21] represent the best results sophisticated hand-crafted feature engineering plus an MLP as the back-end classifier. ii) The majority of recent works belong to the type of pre-transform (or light feature engineering) plus DNNs…”
BackgroundMethod
Research works printed but not linked: 39
- simonyan, 0, Very deep convolutional networks for large-scale image recognition, Proc Int Conf Learn Represent, 1
- 10.1109/TASLP.2019.2915167 · DOI · Paper page
- 10.21437/Interspeech.2019-2341 · DOI
- wu, 0, ASVspoof 2015: The first automatic speaker verification spoofing and countermeasures challenge, Proc INTERSPEECH, 2037
- 10.1109/CVPR.2015.7298594 · DOI · Paper page
- he, 2015, Deep residual learning for image recognition, arXiv 1512 03385
- 10.1109/BTAS.2017.8272715 · DOI
- 10.1109/JSTSP.2016.2647201 · DOI
- kingma, 0, Adam: A method for stochastic optimization, Proc Int Conf Learn Represent, 1
- 10.1109/JSTSP.2017.2684705 · DOI
- 10.1109/JSTSP.2017.2694139 · DOI
- 10.1016/j.csl.2017.01.001 · DOI · Paper page
- 10.1016/j.csl.2017.10.001 · DOI
- 10.1109/TASLP.2019.2946897 · DOI
- 10.1109/APSIPA.2016.7820738 · DOI
- 10.1109/TASLP.2017.2743340 · DOI
- 10.1109/TNNLS.2017.2771947 · DOI
- 10.1109/TIFS.2019.2956589 · DOI
- 10.21437/Interspeech.2019-2892 · DOI
- 10.1109/ICASSP.2018.8462018 · DOI
- 10.21437/Interspeech.2019-1794 · DOI
- 10.1109/TASLP.2017.2723721 · DOI
- 10.1109/TIFS.2015.2398812 · DOI
- lavrentyeva, 0, STC antispoofing systems for the ASVspoof 2019 challenge, Proc INTERSPEECH, 1033
- ar?k, 2018, Neural voice cloning with a few samples, Proc 32nd Int Conf Neural Inf Process Syst, 100�19
- 10.1016/j.specom.2016.04.001 · DOI
- ren, 0, Fastspeech 2: Fast and high-quality end-to-end text to speech, Proc Int Conf Learn Represent, 1
- 10.1109/JSTSP.2017.2682788 · DOI
- 10.1109/JPROC.2013.2251852 · DOI · Paper page
- 10.1109/JSTSP.2016.2647199 · DOI
- 10.1109/ICASSP40776.2020.9053086 · DOI
- 10.21437/Interspeech.2017-1085 · DOI
- 10.1016/j.csl.2020.101105 · DOI
- zhang, 0, Mixup: Beyond empirical risk minimization, Proc Int Conf Learn Represent, 1
- 10.1016/j.specom.2016.10.007 · DOI
- 10.1007/978-3-319-92627-8_16 · DOI
- 10.21437/Interspeech.2019-2505 · DOI
- 10.1109/ICASSP.2017.7952516 · DOI
- 10.1109/TASLP.2017.2732162 · DOI
Cited by
Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543
AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks
Jung, J.-W., Heo, H.-S., Tak, H., Shim, H.-J., Chung, J. S., Lee, B.-J., Yu, H.-J., & Evans, N. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9747766 · Cited by 399
Ilyas, H., Javed, A., & Malik, K. M. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110124 · Cited by 186
A Survey on Speech Deepfake Detection
Li, M., Ahmadiadli, Y., & Zhang, X.-P. (2025) · ACM Computing Surveys · doi:10.1145/3714458 · Cited by 101
“The formula of binary version of CE loss with Softmax is given as: where 𝒙 ∈ R and 𝑦 𝑖 ∈ { 0 , 1 } are the feature embedding and the corresponding label, respectively, and 𝒘 0 , 𝒘 1 ∈ R are the weight vectors for bona fide and Deepfake classes, 𝑁 is the batch size.”
Audio Deepfake Detection With Self-Supervised WavLM And Multi-Fusion Attentive Classifier
Guo, Y., Huang, H., Chen, X., Zhao, H., & Wang, Y. (2024) · ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp48485.2024.10447923 · Cited by 95
Metadata
- Authors
- Hua, G., Teoh, A. B. J., & Zhang, H.
- Venue
- IEEE Signal Processing Letters
- Published
- 2021
- Volume
- 28
- Pages
- 1265-1269
- ISSN
- 1070-9908 (ISSN-L)
- 1558-2361
- OpenAlex
- W3170179936
- Cited by
- 176
- References
- 8
- FWCI
- 9.00
- Type
- journal article
- Language
- en
- Open access
- green
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: Towards End-to-End Synthetic Speech Detection. https://app.cochat.ai/papers/10.1109/lsp.2021.3089437
- The paper
- Hua, G., Teoh, A. B. J., & Zhang, H. (2021). Towards End-to-End Synthetic Speech Detection. IEEE Signal Processing Letters. https://doi.org/10.1109/lsp.2021.3089437
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.