---
title: "RTCFake — paper by Xue et al. (2026) — summary and ideas"
description: "The authors built RTCFake, which they describe as the first large-scale deepfake corpus recorded under real-time… 49 references."
authors: ["Jun Xue", "Zhuolin Yi", "Yihuan Huang", "Yanzhen Ren", "Yujie Chen", "Cunhang Fan", "Zicheng Su", "Yongcheng Zhang", "Bo Cai"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.285/"
doi: "10.18653/v1/2026.findings-acl.285"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/xue-2026-rtcfake-speech-deepfake-detection-real/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xue-2026-rtcfake-speech-deepfake-detection-real/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/48/) / RTCFake: Speech Deepfake Detection in Real-Time Communication

# RTCFake: Speech Deepfake Detection in Real-Time Communication

**Authors:** Jun Xue, Zhuolin Yi, Yihuan Huang, Yanzhen Ren, [Yujie Chen](https://md.research.elamur.ai/free/en/authors/yujie-chen/), Cunhang Fan, Zicheng Su, Yongcheng Zhang and Bo Cai · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.285/) · [PDF](https://aclanthology.org/2026.findings-acl.285.pdf) · [DOI 10.18653/v1/2026.findings-acl.285](https://doi.org/10.18653/v1/2026.findings-acl.285) · [OpenAlex](https://openalex.org/W7166855072)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Voice deepfakes are increasingly used in live calls and video meetings. Most detectors, however, are trained and tested on offline audio or on simulated codec distortions. Real platforms process audio as a black box: noise suppression, echo cancellation, codecs, packet loss and gain control all interact and can erase subtle synthesis artifacts. The authors built RTCFake, which they describe as the first large-scale deepfake corpus recorded under real-time communication (RTC) conditions. They sent real and synthetic speech through seven commercial messaging and conferencing apps, producing precisely paired offline/online versions of each utterance. Their analysis found that phoneme-level representations remain far more stable across transmission than frame-level ones. On that basis they propose phoneme-guided consistency learning (PCL), which makes the embeddings of each phoneme agree between the untransmitted and transmitted versions of an utterance, pushing the detector toward platform-invariant cues. PCL improves robustness to unseen platforms and unseen noise and is more stable than a frame-level consistency constraint. The resource gives a realistic benchmark for securing voice-based identity checks in online meetings.

## Key points
- RTCFake contains about 600 hours of audio. Real speech comes from LibriHeavy (English) and Chinese-Lips (Chinese), and fakes come from 7 TTS and 3 VC systems (e.g., F5-TTS, IndexTTS2, CosyVoice, SeedVC). It is released at huggingface.co/datasets/JunXueTech/RTCFake.
- Transmission platforms are Zoom, WeChat, QQ, DingTalk, Lark, VooV and Telegram. Transcripts of the received audio were checked against the originals, and samples with mismatched content were discarded.
- The data has train, dev and eval splits. The evaluation set adds unseen platforms and unseen noise: office, coffee shop, echo, and three environmental noise types.
- In ablation (EER averaged over offline and online evaluation), frame-level features with PCL gave the best result at 5.81%. The other configurations scored 6.55% (frame + FCL), 7.52% (phoneme + PCL) and 8.34% (phoneme + FCL).
- PCL varied less than FCL as the weighting factor λ changed. Simply mixing offline and online training data gave inconsistent gains under unseen noise.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) — University, Beijing, China · 86 works · 9,097 citations
- [Wuhan University](https://md.research.elamur.ai/free/en/universities/wuhan-university/) — University, Wuhan, China · 47 works · 1,246 citations
- [Anhui University](https://md.research.elamur.ai/free/en/universities/anhui-university/) — University, Hefei, China · 11 works · 7 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 493 works

## Cite

Cite as: Jun Xue, Zhuolin Yi, Yihuan Huang, Yanzhen Ren, Yujie Chen, Cunhang Fan, Zicheng Su, Yongcheng Zhang and Bo Cai. 2026. RTCFake: Speech Deepfake Detection in Real-Time Communication. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{xue2026rtcfake,
  title = {{RTCFake: Speech Deepfake Detection in Real-Time Communication}},
  author = {Jun Xue, Zhuolin Yi, Yihuan Huang, Yanzhen Ren, Yujie Chen, Cunhang Fan, Zicheng Su, Yongcheng Zhang and Bo Cai},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.285},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.285}
}
```

- [← previous RST-Guarder: Enhancing Long-Context Robustness for Safeguards via RST Parsing and Probabilistic Inference](https://md.research.elamur.ai/free/en/papers/zhang-2026-rst-guarder-enhancing-long-context/)
- [next → Russian Generative Spelling, Punctuation and Capitalization Correction](https://md.research.elamur.ai/free/en/papers/martynov-2026-russian-generative-spelling-punctuation-capitalization/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/48/)

## References

49 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. 2025. [https://www.volcengine.com/docs/6561/](https://www.volcengine.com/docs/6561/) 1257584?lang=en. [↗](https://www.volcengine.com/docs/6561/)
2. Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, and 1 others. 2022. [Xls-r: Self-supervised cross-lingual speech representation learning at scale](https://md.research.elamur.ai/free/en/papers/babu-2021-xls-r-self-supervised-cross/). In Proc.
3. Interspeech 2022, pages 2278–2282. [find](https://scholar.google.com/scholar?q=Interspeech+2022%2C+pages+2278%E2%80%932282%2E)
4. Channel News Asia. 2025. Company finance director nearly loses over US$499,000 to scammers using deepfake to impersonate ceo. Accessed: 2025-11-6. [find](https://scholar.google.com/scholar?q=Channel+News+Asia%2E+2025%2E+Company+finance+director+nearly+loses+over+US%24499%2C000+to+scammers+using+deepfake+to+impersonate+ceo%2E+Accessed%3A+2025%2D11%2D6%2E)
5. Yushen Chen, Zhikang Niu, Ziyang Ma, Keqi Deng, Chunhui Wang, JianZhao JianZhao, Kai Yu, and Xie Chen. 2025. [F5-tts: A fairytaler that fakes fluent and faithful speech with flow matching](https://md.research.elamur.ai/free/en/papers/chen-2025-f5-tts-fairytaler-that-fakes/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Paper…
6. Jiawei Du, I-Ming Lin, I-Hsiang Chiu, Xuanjun Chen, Haibin Wu, Wenze Ren, Yu Tsao, Hung-yi Lee, and Jyh-Shing Roger Jang. 2024a. Dfadd: The diffusion and flow-matching based audio deepfake dataset. In 2024 IEEE Spoken Language Technology Workshop (SLT), pages 921–928. IEEE. [find](https://scholar.google.com/scholar?q=Jiawei+Du%2C+I%2DMing+Lin%2C+I%2DHsiang+Chiu%2C+Xuanjun+Chen%2C+Haibin+Wu%2C+Wenze+Ren%2C+Yu+Tsao%2C+Hung%2Dyi+Lee%2C+and+Jyh%2DShing+Roger+Jang%2E+2024a%2E+Dfadd%3A+The+diffusion+and+flow%2Dmatching+based+audio+deepfake+dataset%2E+In)
7. Zhihao Du, Qian Chen, Shiliang Zhang, Kai Hu, Heng Lu, Yexin Yang, Hangrui Hu, Siqi Zheng, Yue Gu, Ziyang Ma, and 1 others. 2024b. [Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens](https://md.research.elamur.ai/free/en/papers/du-2024-cosyvoice-scalable-multilingual-zero-shot/). arXiv preprint arXiv:2407.05407.
8. Cunhang Fan, Mingming Ding, Jianhua Tao, Ruibo Fu, Jiangyan Yi, Zhengqi Wen, and Zhao Lv. 2024a. Dual-branch knowledge distillation for noise-robust synthetic speech detection. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 32:2453–2466. [find](https://scholar.google.com/scholar?q=Cunhang+Fan%2C+Mingming+Ding%2C+Jianhua+Tao%2C+Ruibo+Fu%2C+Jiangyan+Yi%2C+Zhengqi+Wen%2C+and+Zhao+Lv%2E+2024a%2E+Dual%2Dbranch+knowledge+distillation+for+noise%2Drobust+synthetic+speech+detection%2E+IEEE%2FACM+Transactions+o)
9. Cunhang Fan, Jun Xue, Jianhua Tao, Jiangyan Yi, Chenglong Wang, Chengshi Zheng, and Zhao Lv. 2024b. Spatial reconstructed local attention res2net with f0 subband for fake speech detection. Neural Networks, 175:106320. [find](https://scholar.google.com/scholar?q=Cunhang+Fan%2C+Jun+Xue%2C+Jianhua+Tao%2C+Jiangyan+Yi%2C+Chenglong+Wang%2C+Chengshi+Zheng%2C+and+Zhao+Lv%2E+2024b%2E+Spatial+reconstructed+local+attention+res2net+with+f0+subband+for+fake+speech+detection%2E+Neural+Netw)
10. Wen Huang, Yanmei Gu, Zhiming Wang, Huijia Zhu, and Yanmin Qian. 2025. Speechfake: A large-scale multilingual speech deepfake dataset incorporating cutting-edge generation methods. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pag… [find](https://scholar.google.com/scholar?q=Wen+Huang%2C+Yanmei+Gu%2C+Zhiming+Wang%2C+Huijia+Zhu%2C+and+Yanmin+Qian%2E+2025%2E+Speechfake%3A+A+large%2Dscale+multilingual+speech+deepfake+dataset+incorporating+cutting%2Dedge+generation+methods%2E+In+Proceedings+of+t)
11. Jee-weon Jung, Hee-Soo Heo, Hemlata Tak, Hye-jin Shim, Joon Son Chung, Bong-Jin Lee, Ha-Jin Yu, and Nicholas Evans. 2022. Aasist: Audio anti-spoofing using integrated spectro-temporal graph attention networks. In ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processi… [find](https://scholar.google.com/scholar?q=Jee%2Dweon+Jung%2C+Hee%2DSoo+Heo%2C+Hemlata+Tak%2C+Hye%2Djin+Shim%2C+Joon+Son+Chung%2C+Bong%2DJin+Lee%2C+Ha%2DJin+Yu%2C+and+Nicholas+Evans%2E+2022%2E+Aasist%3A+Audio+anti%2Dspoofing+using+integrated+spectro%2Dtemporal+graph+attention+)
12. Jee-weon Jung, Yihan Wu, Xin Wang, Ji-Hoon Kim, Soumi Maiti, Yuta Matsunaga, Hye-jin Shim, Jinchuan Tian, Nicholas Evans, Joon Son Chung, and 1 others. 2025. Spoofceleb: Speech deepfake detection and sasv in the wild. IEEE Open Journal of Signal Processing. [find](https://scholar.google.com/scholar?q=Jee%2Dweon+Jung%2C+Yihan+Wu%2C+Xin+Wang%2C+Ji%2DHoon+Kim%2C+Soumi+Maiti%2C+Yuta+Matsunaga%2C+Hye%2Djin+Shim%2C+Jinchuan+Tian%2C+Nicholas+Evans%2C+Joon+Son+Chung%2C+and+1+others%2E+2025%2E+Spoofceleb%3A+Speech+deepfake+detection+and+)
13. Wei Kang, Xiaoyu Yang, Zengwei Yao, Fangjun Kuang, Yifan Yang, Liyong Guo, Long Lin, and Daniel Povey. 2024. Libriheavy: A 50,000 hours asr corpus with punctuation casing and context. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 10991–1… [find](https://scholar.google.com/scholar?q=Wei+Kang%2C+Xiaoyu+Yang%2C+Zengwei+Yao%2C+Fangjun+Kuang%2C+Yifan+Yang%2C+Liyong+Guo%2C+Long+Lin%2C+and+Daniel+Povey%2E+2024%2E+Libriheavy%3A+A+50%2C000+hours+asr+corpus+with+punctuation+casing+and+context%2E+In+ICASSP+2024%2D2)
14. Xinfeng Li, Kai Li, Yifan Zheng, Chen Yan, Xiaoyu Ji, and Wenyuan Xu. 2024a. Safeear: Content privacy-preserving audio deepfake detection. In Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, pages 3585– 3599. [find](https://scholar.google.com/scholar?q=Xinfeng+Li%2C+Kai+Li%2C+Yifan+Zheng%2C+Chen+Yan%2C+Xiaoyu+Ji%2C+and+Wenyuan+Xu%2E+2024a%2E+Safeear%3A+Content+privacy%2Dpreserving+audio+deepfake+detection%2E+In+Proceedings+of+the+2024+on+ACM+SIGSAC+Conference+on+Comput)
15. Yuang Li, Min Zhang, Mengxin Ren, Xiaosong Qiao, Miaomiao Ma, Daimeng Wei, and Hao Yang. 2024b. Cross-domain audio deepfake detection: Dataset and analysis. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4977–4983. [find](https://scholar.google.com/scholar?q=Yuang+Li%2C+Min+Zhang%2C+Mengxin+Ren%2C+Xiaosong+Qiao%2C+Miaomiao+Ma%2C+Daimeng+Wei%2C+and+Hao+Yang%2E+2024b%2E+Cross%2Ddomain+audio+deepfake+detection%3A+Dataset+and+analysis%2E+In+Proceedings+of+the+2024+Conference+on+Em)
16. Shijia Liao, Yuxuan Wang, Tianyu Li, Yifan Cheng, Ruoyi Zhang, Rongzhi Zhou, and Yijin Xing. 2024. Fish-speech: Leveraging large language models for advanced multilingual text-to-speech synthesis. arXiv preprint arXiv:2411.01156. — [arXiv:2411.01156](https://arxiv.org/abs/2411.01156) [find](https://scholar.google.com/scholar?q=Shijia+Liao%2C+Yuxuan+Wang%2C+Tianyu+Li%2C+Yifan+Cheng%2C+Ruoyi+Zhang%2C+Rongzhi+Zhou%2C+and+Yijin+Xing%2E+2024%2E+Fish%2Dspeech%3A+Leveraging+large+language+models+for+advanced+multilingual+text%2Dto%2Dspeech+synthesis%2E+arX)
17. Songting Liu. 2024. Zero-shot voice conversion with diffusion transformers. arXiv preprint arXiv:2411.09943. — [arXiv:2411.09943](https://arxiv.org/abs/2411.09943) [find](https://scholar.google.com/scholar?q=Songting+Liu%2E+2024%2E+Zero%2Dshot+voice+conversion+with+diffusion+transformers%2E+arXiv+preprint+arXiv%3A2411%2E09943%2E+%E2%80%94+%5BarXiv%3A2411%2E09943%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2411%2E09943%29)
18. Xuechen Liu, Xin Wang, Md Sahidullah, Jose Patino, Héctor Delgado, Tomi Kinnunen, Massimiliano Todisco, Junichi Yamagishi, Nicholas Evans, Andreas Nautsch, and 1 others. 2023. [find](https://scholar.google.com/scholar?q=Xuechen+Liu%2C+Xin+Wang%2C+Md+Sahidullah%2C+Jose+Patino%2C+H%C3%A9ctor+Delgado%2C+Tomi+Kinnunen%2C+Massimiliano+Todisco%2C+Junichi+Yamagishi%2C+Nicholas+Evans%2C+Andreas+Nautsch%2C+and+1+others%2E+2023%2E)
19. Asvspoof 2021: Towards spoofed and deepfake speech detection in the wild. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:2507–2522. [find](https://scholar.google.com/scholar?q=Asvspoof+2021%3A+Towards+spoofed+and+deepfake+speech+detection+in+the+wild%2E+IEEE%2FACM+Transactions+on+Audio%2C+Speech%2C+and+Language+Processing%2C+31%3A2507%E2%80%932522%2E)
20. Nicolas M Müller, Piotr Kawa, Wei Herng Choong, Edresson Casanova, Eren Gölge, Thorsten Müller, Piotr Syga, Philip Sperl, and Konstantin Böttinger. 2024. Mlaad: The multi-language audio anti-spoofing dataset. In 2024 International Joint Conference on Neural Networks (IJCNN), pages 1–7. IEEE. [find](https://scholar.google.com/scholar?q=Nicolas+M+M%C3%BCller%2C+Piotr+Kawa%2C+Wei+Herng+Choong%2C+Edresson+Casanova%2C+Eren+G%C3%B6lge%2C+Thorsten+M%C3%BCller%2C+Piotr+Syga%2C+Philip+Sperl%2C+and+Konstantin+B%C3%B6ttinger%2E+2024%2E+Mlaad%3A+The+multi%2Dlanguage+audio+anti%2Dspoofing+)
21. Karol J Piczak. 2015. Esc: Dataset for environmental sound classification. In Proceedings of the 23rd ACM international conference on Multimedia, pages 1015– 1018. [find](https://scholar.google.com/scholar?q=Karol+J+Piczak%2E+2015%2E+Esc%3A+Dataset+for+environmental+sound+classification%2E+In+Proceedings+of+the+23rd+ACM+international+conference+on+Multimedia%2C+pages+1015%E2%80%93+1018%2E)
22. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. [Robust speech recognition via large-scale weak supervision](https://md.research.elamur.ai/free/en/papers/radford-2022-robust-speech-recognition-large-scale/). In International conference on machine learning, pages 28492–28518. PMLR.
23. Resemble AI. 2025. Chatterbox-TTS. [https://github.com/resemble-ai/chatterbox](https://github.com/resemble-ai/chatterbox). GitHub repository. [↗](https://github.com/resemble-ai/chatterbox)
24. Hemlata Tak, Madhu Kamble, Jose Patino, Massimiliano Todisco, and Nicholas Evans. 2022a. Rawboost: A raw data boosting and augmentation method applied to automatic speaker verification anti-spoofing. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP… [find](https://scholar.google.com/scholar?q=Hemlata+Tak%2C+Madhu+Kamble%2C+Jose+Patino%2C+Massimiliano+Todisco%2C+and+Nicholas+Evans%2E+2022a%2E+Rawboost%3A+A+raw+data+boosting+and+augmentation+method+applied+to+automatic+speaker+verification+anti%2Dspoofing%2E+)
25. Hemlata Tak, Massimiliano Todisco, Xin Wang, Jee-weon Jung, Junichi Yamagishi, and Nicholas Evans. 2022b. Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation. In The Speaker and Language Recognition Workshop (Odyssey 2022). ISCA. [find](https://scholar.google.com/scholar?q=Hemlata+Tak%2C+Massimiliano+Todisco%2C+Xin+Wang%2C+Jee%2Dweon+Jung%2C+Junichi+Yamagishi%2C+and+Nicholas+Evans%2E+2022b%2E+Automatic+speaker+verification+spoofing+and+deepfake+detection+using+wav2vec+2%2E0+and+data+augm)
26. Massimiliano Todisco, Xin Wang, Ville Vestman, Md Sahidullah, Hector Delgado, Andreas Nautsch, Junichi Yamagishi, Nicholas Evans, Tomi Kinnunen, and Kong Aik Lee. 2019. [find](https://scholar.google.com/scholar?q=Massimiliano+Todisco%2C+Xin+Wang%2C+Ville+Vestman%2C+Md+Sahidullah%2C+Hector+Delgado%2C+Andreas+Nautsch%2C+Junichi+Yamagishi%2C+Nicholas+Evans%2C+Tomi+Kinnunen%2C+and+Kong+Aik+Lee%2E+2019%2E)
27. Asvspoof 2019: Future horizons in spoofed and fake audio detection. In Interspeech 2019, pages 1008–1012. International Speech Communication Association. [find](https://scholar.google.com/scholar?q=Asvspoof+2019%3A+Future+horizons+in+spoofed+and+fake+audio+detection%2E+In+Interspeech+2019%2C+pages+1008%E2%80%931012%2E+International+Speech+Communication+Association%2E)
28. Xin Wang, Héctor Delgado, Hemlata Tak, Jee-Weon Jung, Hye-Jin Shim, Massimiliano Todisco, Ivan Kukanov, Xuechen Liu, Md Sahidullah, Tomi Kinnunen, and 1 others. 2024. Asvspoof 5: crowdsourced speech data, deepfakes, and adversarial attacks at scale. In The Automatic Speaker Verification Spoofing Cou… [find](https://scholar.google.com/scholar?q=Xin+Wang%2C+H%C3%A9ctor+Delgado%2C+Hemlata+Tak%2C+Jee%2DWeon+Jung%2C+Hye%2DJin+Shim%2C+Massimiliano+Todisco%2C+Ivan+Kukanov%2C+Xuechen+Liu%2C+Md+Sahidullah%2C+Tomi+Kinnunen%2C+and+1+others%2E+2024%2E+Asvspoof+5%3A+crowdsourced+speech+d)
29. Xinsheng Wang, Mingqi Jiang, Ziyang Ma, Ziyu Zhang, Songxiang Liu, Linqin Li, Zheng Liang, Qixi Zheng, Rui Wang, Xiaoqin Feng, and 1 others. 2025. Spark-tts: An efficient llm-based text-to-speech model with single-stream decoupled speech tokens. arXiv preprint arXiv:2503.01710. — [arXiv:2503.01710](https://arxiv.org/abs/2503.01710) [find](https://scholar.google.com/scholar?q=Xinsheng+Wang%2C+Mingqi+Jiang%2C+Ziyang+Ma%2C+Ziyu+Zhang%2C+Songxiang+Liu%2C+Linqin+Li%2C+Zheng+Liang%2C+Qixi+Zheng%2C+Rui+Wang%2C+Xiaoqin+Feng%2C+and+1+others%2E+2025%2E+Spark%2Dtts%3A+An+efficient+llm%2Dbased+text%2Dto%2Dspeech+mode)
30. Haibin Wu, Yuan Tseng, and Hung-yi Lee. 2024. Codecfake: Enhancing anti-spoofing models against deepfake audios from codec-based speech synthesis systems. In Proc. [find](https://scholar.google.com/scholar?q=Haibin+Wu%2C+Yuan+Tseng%2C+and+Hung%2Dyi+Lee%2E+2024%2E+Codecfake%3A+Enhancing+anti%2Dspoofing+models+against+deepfake+audios+from+codec%2Dbased+speech+synthesis+systems%2E+In+Proc%2E)
31. Interspeech 2024, pages 1770– 1774. [find](https://scholar.google.com/scholar?q=Interspeech+2024%2C+pages+1770%E2%80%93+1774%2E)
32. Yuankun Xie, Ruibo Fu, Xiaopeng Wang, Zhiyong Wang, Ya Li, Zhengqi Wen, Haonnan Cheng, and Long Ye. 2025a. Fake speech wild: Detecting deepfake speech on social media platform. arXiv preprint arXiv:2508.10559. — [arXiv:2508.10559](https://arxiv.org/abs/2508.10559) [find](https://scholar.google.com/scholar?q=Yuankun+Xie%2C+Ruibo+Fu%2C+Xiaopeng+Wang%2C+Zhiyong+Wang%2C+Ya+Li%2C+Zhengqi+Wen%2C+Haonnan+Cheng%2C+and+Long+Ye%2E+2025a%2E+Fake+speech+wild%3A+Detecting+deepfake+speech+on+social+media+platform%2E+arXiv+preprint+arXiv%3A25)
33. Yuankun Xie, Yi Lu, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Jianhua Tao, Xin Qi, Xiaopeng Wang, Yukun Liu, Haonan Cheng, and 1 others. 2025b. The codecfake dataset and countermeasures for the universally detection of deepfake audio. IEEE Transactions on Audio, Speech and Language Processing. [find](https://scholar.google.com/scholar?q=Yuankun+Xie%2C+Yi+Lu%2C+Ruibo+Fu%2C+Zhengqi+Wen%2C+Zhiyong+Wang%2C+Jianhua+Tao%2C+Xin+Qi%2C+Xiaopeng+Wang%2C+Yukun+Liu%2C+Haonan+Cheng%2C+and+1+others%2E+2025b%2E+The+codecfake+dataset+and+countermeasures+for+the+universally)
34. Qiantong Xu, Alexei Baevski, and Michael Auli. 2022. Simple and effective zero-shot cross-lingual phoneme recognition. In Proc. [find](https://scholar.google.com/scholar?q=Qiantong+Xu%2C+Alexei+Baevski%2C+and+Michael+Auli%2E+2022%2E+Simple+and+effective+zero%2Dshot+cross%2Dlingual+phoneme+recognition%2E+In+Proc%2E)
35. Interspeech 2022, pages 2113– 2117. [find](https://scholar.google.com/scholar?q=Interspeech+2022%2C+pages+2113%E2%80%93+2117%2E)
36. Jun Xue, Cunhang Fan, Zhao Lv, Jianhua Tao, Jiangyan Yi, Chengshi Zheng, Zhengqi Wen, Minmin Yuan, and Shegang Shao. 2022. Audio deepfake detection based on a combination of f0 information and real plus imaginary spectrogram features. In Proceedings of the 1st international workshop on deepfake dete… [find](https://scholar.google.com/scholar?q=Jun+Xue%2C+Cunhang+Fan%2C+Zhao+Lv%2C+Jianhua+Tao%2C+Jiangyan+Yi%2C+Chengshi+Zheng%2C+Zhengqi+Wen%2C+Minmin+Yuan%2C+and+Shegang+Shao%2E+2022%2E+Audio+deepfake+detection+based+on+a+combination+of+f0+information+and+real+pl)
37. Jun Xue, Cunhang Fan, Jiangyan Yi, Chenglong Wang, Zhengqi Wen, Dan Zhang, and Zhao Lv. 2023. Learning from yourself: A self-distillation method for fake speech detection. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE. [find](https://scholar.google.com/scholar?q=Jun+Xue%2C+Cunhang+Fan%2C+Jiangyan+Yi%2C+Chenglong+Wang%2C+Zhengqi+Wen%2C+Dan+Zhang%2C+and+Zhao+Lv%2E+2023%2E+Learning+from+yourself%3A+A+self%2Ddistillation+method+for+fake+speech+detection%2E+In+ICASSP+2023%2D2023+IEEE+Int)
38. Jun Xue, Cunhang Fan, Jiangyan Yi, Jian Zhou, and Zhao Lv. 2024. Dynamic ensemble teacher-student distillation framework for light-weight fake audio detection. IEEE Signal Processing Letters, 31:2305– 2309. [find](https://scholar.google.com/scholar?q=Jun+Xue%2C+Cunhang+Fan%2C+Jiangyan+Yi%2C+Jian+Zhou%2C+and+Zhao+Lv%2E+2024%2E+Dynamic+ensemble+teacher%2Dstudent+distillation+framework+for+light%2Dweight+fake+audio+detection%2E+IEEE+Signal+Processing+Letters%2C+31%3A2305%E2%80%93)
39. Junichi Yamagishi, Xin Wang, Massimiliano Todisco, Md Sahidullah, Jose Patino, Andreas Nautsch, Xuechen Liu, Kong Aik Lee, Tomi Kinnunen, Nicholas Evans, and 1 others. 2021. [find](https://scholar.google.com/scholar?q=Junichi+Yamagishi%2C+Xin+Wang%2C+Massimiliano+Todisco%2C+Md+Sahidullah%2C+Jose+Patino%2C+Andreas+Nautsch%2C+Xuechen+Liu%2C+Kong+Aik+Lee%2C+Tomi+Kinnunen%2C+Nicholas+Evans%2C+and+1+others%2E+2021%2E)
40. Asvspoof 2021: accelerating progress in spoofed and deepfake speech detection. In Proc. [find](https://scholar.google.com/scholar?q=Asvspoof+2021%3A+accelerating+progress+in+spoofed+and+deepfake+speech+detection%2E+In+Proc%2E)
41. Zhen Ye, Xinfa Zhu, Chi-Min Chan, Xinsheng Wang, Xu Tan, Jiahe Lei, Yi Peng, Haohe Liu, Yizhu Jin, Zheqi Dai, and 1 others. 2025. Llasa: Scaling train-time and inference-time compute for llama-based speech synthesis. arXiv preprint arXiv:2502.04128. — [arXiv:2502.04128](https://arxiv.org/abs/2502.04128) [find](https://scholar.google.com/scholar?q=Zhen+Ye%2C+Xinfa+Zhu%2C+Chi%2DMin+Chan%2C+Xinsheng+Wang%2C+Xu+Tan%2C+Jiahe+Lei%2C+Yi+Peng%2C+Haohe+Liu%2C+Yizhu+Jin%2C+Zheqi+Dai%2C+and+1+others%2E+2025%2E+Llasa%3A+Scaling+train%2Dtime+and+inference%2Dtime+compute+for+llama%2Dbased+s)
42. Jiangyan Yi, Ruibo Fu, Jianhua Tao, Shuai Nie, Haoxin Ma, Chenglong Wang, Tao Wang, Zhengkun Tian, Ye Bai, Cunhang Fan, and 1 others. 2022. [find](https://scholar.google.com/scholar?q=Jiangyan+Yi%2C+Ruibo+Fu%2C+Jianhua+Tao%2C+Shuai+Nie%2C+Haoxin+Ma%2C+Chenglong+Wang%2C+Tao+Wang%2C+Zhengkun+Tian%2C+Ye+Bai%2C+Cunhang+Fan%2C+and+1+others%2E+2022%2E)
43. Add 2022: the first audio deep synthesis detection challenge. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 9216–9220. IEEE. [find](https://scholar.google.com/scholar?q=Add+2022%3A+the+first+audio+deep+synthesis+detection+challenge%2E+In+ICASSP+2022%2D2022+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%28ICASSP%29%2C+pages+9216%E2%80%939220%2E+IEEE%2E)
44. Jiangyan Yi, Jianhua Tao, Ruibo Fu, Xinrui Yan, Chenglong Wang, Tao Wang, Chu Yuan Zhang, Xiaohui Zhang, Yan Zhao, Yong Ren, and 1 others. 2023. [find](https://scholar.google.com/scholar?q=Jiangyan+Yi%2C+Jianhua+Tao%2C+Ruibo+Fu%2C+Xinrui+Yan%2C+Chenglong+Wang%2C+Tao+Wang%2C+Chu+Yuan+Zhang%2C+Xiaohui+Zhang%2C+Yan+Zhao%2C+Yong+Ren%2C+and+1+others%2E+2023%2E)
45. Add 2023: the second audio deepfake detection challenge. arXiv preprint arXiv:2305.13774. — [arXiv:2305.13774](https://arxiv.org/abs/2305.13774) [find](https://scholar.google.com/scholar?q=Add+2023%3A+the+second+audio+deepfake+detection+challenge%2E+arXiv+preprint+arXiv%3A2305%2E13774%2E+%E2%80%94+%5BarXiv%3A2305%2E13774%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2305%2E13774%29)
46. Qishan Zhang, Shuangbing Wen, and Tao Hu. 2024. Audio deepfake detection with self-supervised xls-r and sls classifier. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 6765– 6773. [find](https://scholar.google.com/scholar?q=Qishan+Zhang%2C+Shuangbing+Wen%2C+and+Tao+Hu%2E+2024%2E+Audio+deepfake+detection+with+self%2Dsupervised+xls%2Dr+and+sls+classifier%2E+In+Proceedings+of+the+32nd+ACM+International+Conference+on+Multimedia%2C+pages+676)
47. Jinghua Zhao, Yuhang Jia, Shiyao Wang, Jiaming Zhou, Hui Wang, and Yong Qin. 2025. Chinese-lips: A chinese audio-visual speech recognition dataset with lip-reading and presentation slides. arXiv preprint arXiv:2504.15066. — [arXiv:2504.15066](https://arxiv.org/abs/2504.15066) [find](https://scholar.google.com/scholar?q=Jinghua+Zhao%2C+Yuhang+Jia%2C+Shiyao+Wang%2C+Jiaming+Zhou%2C+Hui+Wang%2C+and+Yong+Qin%2E+2025%2E+Chinese%2Dlips%3A+A+chinese+audio%2Dvisual+speech+recognition+dataset+with+lip%2Dreading+and+presentation+slides%2E+arXiv+prepr)
48. Siyi Zhou, Yiquan Zhou, Yi He, Xun Zhou, Jinchao Wang, Wei Deng, and Jingchen Shu. 2025a. Indextts2: A breakthrough in emotionally expressive and duration-controlled auto-regressive zero-shot text-to-speech. arXiv preprint arXiv:2506.21619. — [arXiv:2506.21619](https://arxiv.org/abs/2506.21619) [find](https://scholar.google.com/scholar?q=Siyi+Zhou%2C+Yiquan+Zhou%2C+Yi+He%2C+Xun+Zhou%2C+Jinchao+Wang%2C+Wei+Deng%2C+and+Jingchen+Shu%2E+2025a%2E+Indextts2%3A+A+breakthrough+in+emotionally+expressive+and+duration%2Dcontrolled+auto%2Dregressive+zero%2Dshot+text%2Dto%2D)
49. Yixuan Zhou, Guoyang Zeng, Xin Liu, Xiang Li, Renjie Yu, Ziyang Wang, Runchuan Ye, Weiyue Sun, Jiancheng Gui, Kehan Li, and 1 others. 2025b. Voxcpm: Tokenizer-free tts for context-aware speech generation and true-to-life voice cloning. arXiv preprint arXiv:2509.24650. — [arXiv:2509.24650](https://arxiv.org/abs/2509.24650) [find](https://scholar.google.com/scholar?q=Yixuan+Zhou%2C+Guoyang+Zeng%2C+Xin+Liu%2C+Xiang+Li%2C+Renjie+Yu%2C+Ziyang+Wang%2C+Runchuan+Ye%2C+Weiyue+Sun%2C+Jiancheng+Gui%2C+Kehan+Li%2C+and+1+others%2E+2025b%2E+Voxcpm%3A+Tokenizer%2Dfree+tts+for+context%2Daware+speech+generat)

*Updated 2 November 2026*