Open Challenges in Synthetic Speech Detection
Open accessThe DOI matches its Crossref record; 44 of the 46 references it cites were found in a registry or an index.
Abstract
In this paper the current status and open challenges of synthetic speech detection are addressed. The work comprises an initial analysis of available open datasets and of existing detection methods, a description of the requirements for new research datasets compliant with regulations and better representing real-case scenarios, and a discussion of the desired characteristics of future trustworthy detection methods in terms of both functional and non-functional requirements. Compared to other works, based on specific detection solutions or presenting single dataset of synthetic speeches, our paper is meant to orient future state-of-the-art research in the domain, to quickly lessen the current gap between synthesis and detection approaches.
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
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072 · cited 1×
“The developed system was evaluated on five public datasets, namely the ASVspoof 2019, LibriSpeech [34], LJ Speech [21], Cloud 2019 [35] and the speech tracks of the Interactive Emotional Dyadic Motion Capture [36].”
MethodWaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911 · cited 1×
“Since the very early experiments with WaveNet, the authors of these models noticed that even though their networks could synthesize speech samples with natural segmental quality, the samples sometimes had unnatural prosody by stressing wrong words in a sentence, especially in the case of very short sentences of a few…”
IEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869 · cited 2×
“The developed system was evaluated on five public datasets, namely the ASVspoof 2019, LibriSpeech [35], LJ Speech [21], Cloud 2019 [36] and the speech tracks of the Interactive Emotional Dyadic Motion Capture [37].”
Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
Shen, J., Pang, R., Weiss, R. J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., Skerrv-Ryan, R., et al. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461368 · Cited by 2,791
TIMIT Acoustic-Phonetic Continuous Speech Corpus
Garofolo, J. S., Lamel, L. F., Fisher, W. M., Pallett, D. S., Dahlgren, N. L., Zue, V. W., & Fiscus, J. G. (2020) · Americanae (AECID Library) · doi:10.35111/17gk-bn40 · Cited by 2,508
European Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131 · cited 2×
“The advancements of DNNs and their widespread adoption in many fields of high relevance for the industry – such as computer vision and natural language processing – increased the social impact of AI models and led to a need for regulatory frameworks such as the “right to explanation” of AI systems promoted by the Europ…”
Federated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077 · cited 1×
“There are methods in literature trying to address the issue [44], [45], but the problem is still an open research question.”
Federated Learning on Non-IID Data Silos: An Experimental Study
Li, Q., Diao, Y., Chen, Q., & He, B. (2022) · 2022 IEEE 38th International Conference on Data Engineering (ICDE) · doi:10.1109/icde53745.2022.00077 · Cited by 1,132
“Waveglow: a flow-based generative network for speech synthesis,”
Prenger, R., Valle, R., & Catanzaro, B. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683143 · Cited by 1,004
Cited by
Deepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113
A Robust Approach to Multimodal Deepfake Detection
Salvi, D., Liu, H., Mandelli, S., Bestagini, P., Zhou, W., Zhang, W., & Tubaro, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9060122 · Cited by 96
“To do so, the scientific community has proposed numerous speech deepfake detectors that employ different detection approaches and strategies [24].”
Domain Generalization via Aggregation and Separation for Audio Deepfake Detection
Xie, Y., Cheng, H., Wang, Y., & Ye, L. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3324724 · Cited by 59
“Digital Object Identifier 10.1109/TIFS.2023.3324724 technology, Audio DeepFake Detection (ADD), faces serious challenges [3], [4]: • The existing theoretical studies on the differences between real and fake speech are inadequate.”
BackgroundInfluentialAudio Deepfake Detection by using Machine and Deep Learning
Kılınç, H. H., & Kaledibi, F. (2023) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom59760.2023.10323004 · Cited by 24
“Cuccovillo et al. [8] discussed the current state and challenges of synthetic speech detection and performed an analysis of open datasets and available detection methods.”
MethodTowards Frequency Band Explainability in Synthetic Speech Detection
Salvi, D., Bestagini, P., & Tubaro, S. (2023) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco58844.2023.10289804 · Cited by 30
“Focusing on the audio field, several methods have been proposed in the last few years to tackle synthetic speech detection [3].”
Method
Metadata
- Authors
- Cuccovillo, L., Papastergiopoulos, C., Vafeiadis, A., Yaroshchuk, A., Aichroth, P., Votis, K., & Tzovaras, D.
- Affiliations
- Fraunhofer Institute for Digital Media Technology (DE)
- Centre for Research and Technology Hellas (GR)
- ORCID
- Venue
- 2022 IEEE International Workshop on Information Forensics and Security (WIFS)
- Publisher
- IEEE
- Published
- 2022-12-12
- Pages
- 1-6
- ISSN
- 2157-4774 (ISSN-L)
- OpenAlex
- W4311591887
- Cited by
- 33
- References
- 46
- Citations by year
- 2026: 6 · 2025: 13 · 2024: 5 · 2023: 9
- FWCI
- 3.73
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE International Workshop on Information Forensics and Security (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
- arXiv (Cornell University)
- 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 › Artificial Intelligence › Emotion and Mood Recognition
- Keywords
- synthetic speech detection, speech synthesis, detection dataset, regulatory compliance, non-functional requirements, functional requirements, open problems
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: Open Challenges in Synthetic Speech Detection. https://app.cochat.ai/papers/10.1109/wifs55849.2022.9975433
- The paper
- Cuccovillo, L., Papastergiopoulos, C., Vafeiadis, A., Yaroshchuk, A., Aichroth, P., Votis, K., & Tzovaras, D. (2022). Open Challenges in Synthetic Speech Detection. 2022 IEEE International Workshop on Information Forensics and Security (WIFS). https://doi.org/10.1109/wifs55849.2022.9975433
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.