---
title: "UniVocal: Unified Speech-Singing Code-Switching Synthesis"
description: "The paper introduces Speech-Singing Code-Switching (SCS) Synthesis. 36 references. Among them: 0."
authors: ["YuFei Shi", "Qian Chen", "Wen Wang", "Xiangang Li", "Zhen-Hua Ling", "Yang Ai"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1452/"
doi: "10.18653/v1/2026.acl-long.1452"
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/shi-2026-univocal-unified-speech-singing-code/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shi-2026-univocal-unified-speech-singing-code/)

[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/47/) / UniVocal: Unified Speech-Singing Code-Switching Synthesis

# UniVocal: Unified Speech-Singing Code-Switching Synthesis

**Authors:** YuFei Shi, [Qian Chen](https://md.research.elamur.ai/free/en/authors/qian-chen/), [Wen Wang](https://md.research.elamur.ai/free/en/authors/wen-wang/), [Xiangang Li](https://md.research.elamur.ai/free/en/authors/xiangang-li/), [Zhen-Hua Ling](https://md.research.elamur.ai/free/en/authors/zhen-hua-ling/) and Yang Ai · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1452/) · [PDF](https://aclanthology.org/2026.acl-long.1452.pdf) · [DOI 10.18653/v1/2026.acl-long.1452](https://doi.org/10.18653/v1/2026.acl-long.1452) · [OpenAlex](https://openalex.org/W7166814855)

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

## Summary
The paper introduces Speech-Singing Code-Switching (SCS) Synthesis. In this task, a single generated utterance moves between talking and singing, and the text alone decides where the switches happen. Existing systems either produce only one mode or, like Bark, need explicit switching tags. The authors present UniVocal, built on the CosyVoice 2 TTS backbone. It is trained with a two-stage curriculum: the first stage puts speech and singing into a shared representation space, and the second teaches automatic mode switching. Real SCS recordings are scarce, so the authors use LLMs to write mixed scripts with varied switching cues and voice them with the stage-1 model. They also release a multi-scenario test set, SCSBench. Semantic tokens lose pitch detail, so the model first predicts a fine-grained pitch token and then the content token, in a chain-of-thought style. UniVocal reports state-of-the-art switching accuracy on SCSBench and stays competitive on ordinary speech and singing benchmarks. This matters for expressive voice agents, storytelling and educational audio.

## Key points
- On SCSBench-Mixed, mode-switching F1 is 0.871 (objective) and 0.810 (subjective), beating cascaded baselines. Automatic scoring uses Gemini 2.5 Pro with in-context examples.
- The refined cent token works as follows:
  - Pitch is measured in cents relative to A4 (440 Hz).
  - It is folded into one octave, giving 1200 bins with at most 1 cent of quantization error.
  - Unvoiced frames get the token -1.
  - At each step, one cent token and one semantic token are generated.
- On about 30 minutes of real-world recordings, F1 is only 0.201 (versus 0.452 for the Gemini + Cosy2 + LeVo cascade). Adding one explicit cue phrase per sample raises it to 0.730, above that cascade's 0.691.
- Explicit trigger phrases and humming make switching reliable. Lyrics that rely only on implicit semantic cues often fail to trigger singing.
- Training data comes from LibriTTS and Suno-generated songs. The Suno singing data carries artifacts and lyric misalignment. Code and data are released on GitHub (FunAudioLLM/FunResearch) under a restrictive license.

*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

- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 108 works · 112,698 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 452 works

🧭 Topics (1): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 828 works

## Cite

Cite as: YuFei Shi, Qian Chen, Wen Wang, Xiangang Li, Zhen-Hua Ling and Yang Ai. 2026. UniVocal: Unified Speech-Singing Code-Switching Synthesis. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{shi2026univocal,
  title = {{UniVocal: Unified Speech-Singing Code-Switching Synthesis}},
  author = {YuFei Shi, Qian Chen, Wen Wang, Xiangang Li, Zhen-Hua Ling and Yang Ai},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1452},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1452}
}
```

- [← previous University Speaking for Everyone: Assessing Changes in Italian Higher Education Statutes toward Gender-Inclusive Language](https://md.research.elamur.ai/free/en/papers/salto-2026-university-speaking-everyone-assessing-changes/)
- [next → Unmasking the Factual-Conceptual Gap in Persian Language Models](https://md.research.elamur.ai/free/en/papers/sakhaeirad-2026-unmasking-factual-conceptual-gap-persian/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/47/)

## References

36 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Philip Anastassiou, Jiawei Chen, Jitong Chen, Yuanzhe Chen, Zhuo Chen, Ziyi Chen, Jian Cong, Lelai Deng, Chuang Ding, Lu Gao, and 1 others. 2024. [Seed-tts: A family of high-quality versatile speech generation models](https://md.research.elamur.ai/free/en/papers/anastassiou-2024-seed-tts-family-high/). arXiv preprint arXiv:2406.02430.
2. Yafeng Chen, Siqi Zheng, Hui Wang, Luyao Cheng, Qian Chen, and Jiajun Qi. 2023. An enhanced res2net with local and global feature fusion for speaker verification. arXiv preprint arXiv:2305.12838. — [arXiv:2305.12838](https://arxiv.org/abs/2305.12838) [find](https://scholar.google.com/scholar?q=Yafeng+Chen%2C+Siqi+Zheng%2C+Hui+Wang%2C+Luyao+Cheng%2C+Qian+Chen%2C+and+Jiajun+Qi%2E+2023%2E+An+enhanced+res2net+with+local+and+global+feature+fusion+for+speaker+verification%2E+arXiv+preprint+arXiv%3A2305%2E12838%2E+%E2%80%94+%5Ba)
3. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). arX…
4. Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, and Alexandre Défossez. 2023. Simple and controllable music generation. Advances in Neural Information Processing Systems, 36:47704–47720. [find](https://scholar.google.com/scholar?q=Jade+Copet%2C+Felix+Kreuk%2C+Itai+Gat%2C+Tal+Remez%2C+David+Kant%2C+Gabriel+Synnaeve%2C+Yossi+Adi%2C+and+Alexandre+D%C3%A9fossez%2E+2023%2E+Simple+and+controllable+music+generation%2E+Advances+in+Neural+Information+Processing)
5. Eugene Kharitonov, Ann Lee, Adam Polyak, Yossi Adi, Jade Copet, Kushal Lakhotia, Tu-Anh Nguyen, Morgane Rivière, Abdelrahman Mohamed, Emmanuel Dupoux, and 1 others. 2021. [Text-free prosody-aware generative spoken language modeling](https://md.research.elamur.ai/free/en/papers/kharitonov-2022-text-free-prosody-aware-generative/). arXiv preprint arXiv:2109.03264.
6. Jungil Kong, Jaehyeon Kim, and Jaekyoung Bae. 2020. Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis. Advances in neural information processing systems, 33:17022– 17033. [find](https://scholar.google.com/scholar?q=Jungil+Kong%2C+Jaehyeon+Kim%2C+and+Jaekyoung+Bae%2E+2020%2E+Hifi%2Dgan%3A+Generative+adversarial+networks+for+efficient+and+high+fidelity+speech+synthesis%2E+Advances+in+neural+information+processing+systems%2C+33%3A17)
7. Shun Lei, Yaoxun Xu, Zhiwei Lin, Huaicheng Zhang, Wei Tan, Hangting Chen, Jianwei Yu, Yixuan Zhang, Chenyu Yang, Haina Zhu, and 1 others. 2025. Levo: High-quality song generation with multi-preference alignment. arXiv preprint arXiv:2506.07520. — [arXiv:2506.07520](https://arxiv.org/abs/2506.07520) [find](https://scholar.google.com/scholar?q=Shun+Lei%2C+Yaoxun+Xu%2C+Zhiwei+Lin%2C+Huaicheng+Zhang%2C+Wei+Tan%2C+Hangting+Chen%2C+Jianwei+Yu%2C+Yixuan+Zhang%2C+Chenyu+Yang%2C+Haina+Zhu%2C+and+1+others%2E+2025%2E+Levo%3A+High%2Dquality+song+generation+with+multi%2Dpreference)
8. Yi Lei, Shan Yang, Xinsheng Wang, Qicong Xie, Jixun Yao, Lei Xie, and Dan Su. 2023. Unisyn: an end-to-end unified model for text-to-speech and singing voice synthesis. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 13025–13033. [find](https://scholar.google.com/scholar?q=Yi+Lei%2C+Shan+Yang%2C+Xinsheng+Wang%2C+Qicong+Xie%2C+Jixun+Yao%2C+Lei+Xie%2C+and+Dan+Su%2E+2023%2E+Unisyn%3A+an+end%2Dto%2Dend+unified+model+for+text%2Dto%2Dspeech+and+singing+voice+synthesis%2E+In+Proceedings+of+the+AAAI+Confe)
9. Alexandre Défossez, Jade Copet, Gabriel Synnaeve, and Yossi Adi. 2022. [High fidelity neural audio compression](https://md.research.elamur.ai/free/en/papers/defossez-2022-high-fidelity-neural-audio-compression/). arXiv preprint arXiv:2210.13438.
10. Zihan Liu, Shuangrui Ding, Zhixiong Zhang, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Dahua Lin, and Jiaqi Wang. 2025. Songgen: A single stage auto-regressive transformer for text-to-song generation. arXiv preprint arXiv:2502.13128. — [arXiv:2502.13128](https://arxiv.org/abs/2502.13128) [find](https://scholar.google.com/scholar?q=Zihan+Liu%2C+Shuangrui+Ding%2C+Zhixiong+Zhang%2C+Xiaoyi+Dong%2C+Pan+Zhang%2C+Yuhang+Zang%2C+Yuhang+Cao%2C+Dahua+Lin%2C+and+Jiaqi+Wang%2E+2025%2E+Songgen%3A+A+single+stage+auto%2Dregressive+transformer+for+text%2Dto%2Dsong+genera)
11. Zhihao Du, Qian Chen, Shiliang Zhang, Kai Hu, Heng Lu, Yexin Yang, Hangrui Hu, Siqi Zheng, Yue Gu, Ziyang Ma, and 1 others. 2024a. Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens. arXiv preprint arXiv:2407.05407. [find](https://scholar.google.com/scholar?q=Zhihao+Du%2C+Qian+Chen%2C+Shiliang+Zhang%2C+Kai+Hu%2C+Heng+Lu%2C+Yexin+Yang%2C+Hangrui+Hu%2C+Siqi+Zheng%2C+Yue+Gu%2C+Ziyang+Ma%2C+and+1+others%2E+2024a%2E+Cosyvoice%3A+A+scalable+multilingual+zero%2Dshot+text%2Dto%2Dspeech+synthesiz)
12. Tu Anh Nguyen, Wei-Ning Hsu, Antony d’Avirro, Bowen Shi, Itai Gat, Maryam Fazel-Zarani, Tal Remez, Jade Copet, Gabriel Synnaeve, Michael Hassid, and 1 others. 2023. Expresso: A benchmark and analysis of discrete expressive speech resynthesis. arXiv preprint arXiv:2308.05725. — [arXiv:2308.05725](https://arxiv.org/abs/2308.05725) [find](https://scholar.google.com/scholar?q=Tu+Anh+Nguyen%2C+Wei%2DNing+Hsu%2C+Antony+d%E2%80%99Avirro%2C+Bowen+Shi%2C+Itai+Gat%2C+Maryam+Fazel%2DZarani%2C+Tal+Remez%2C+Jade+Copet%2C+Gabriel+Synnaeve%2C+Michael+Hassid%2C+and+1+others%2E+2023%2E+Expresso%3A+A+benchmark+and+analysis+)
13. Zhihao Du, Yuxuan Wang, Qian Chen, Xian Shi, Xiang Lv, Tianyu Zhao, Zhifu Gao, Yexin Yang, Changfeng Gao, Hui Wang, and 1 others. 2024b. Cosyvoice 2: Scalable streaming speech synthesis with large language models. arXiv preprint arXiv:2412.10117. [find](https://scholar.google.com/scholar?q=Zhihao+Du%2C+Yuxuan+Wang%2C+Qian+Chen%2C+Xian+Shi%2C+Xiang+Lv%2C+Tianyu+Zhao%2C+Zhifu+Gao%2C+Yexin+Yang%2C+Changfeng+Gao%2C+Hui+Wang%2C+and+1+others%2E+2024b%2E+Cosyvoice+2%3A+Scalable+streaming+speech+synthesis+with+large+lan)
14. Ziqian Ning, Shuai Wang, Yuepeng Jiang, Jixun Yao, Lei He, Shifeng Pan, Jie Ding, and Lei Xie. 2025. Drop the beat! freestyler for accompaniment conditioned rapping voice generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 24966–24974. [find](https://scholar.google.com/scholar?q=Ziqian+Ning%2C+Shuai+Wang%2C+Yuepeng+Jiang%2C+Jixun+Yao%2C+Lei+He%2C+Shifeng+Pan%2C+Jie+Ding%2C+and+Lei+Xie%2E+2025%2E+Drop+the+beat%21+freestyler+for+accompaniment+conditioned+rapping+voice+generation%2E+In+Proceedings+of)
15. Chitralekha Gupta, Haizhou Li, and Ye Wang. 2017. Perceptual evaluation of singing quality. In Proc. APSIPA, pages 577–586. IEEE. [find](https://scholar.google.com/scholar?q=Chitralekha+Gupta%2C+Haizhou+Li%2C+and+Ye+Wang%2E+2017%2E+Perceptual+evaluation+of+singing+quality%2E+In+Proc%2E+APSIPA%2C+pages+577%E2%80%93586%2E+IEEE%2E)
16. Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. [Hubert: Self-supervised speech representation learning by masked prediction of hidden units](https://md.research.elamur.ai/free/en/papers/hsu-2021-hubert-self-supervised-speech-representation/). IEEE/ACM transactions on audio, speech, and language processing, 29:3451–3460.
17. Changhao Pan, Dongyu Yao, Yu Zhang, Wenxiang Guo, Jingyu Lu, Zhiyuan Zhu, and Zhou Zhao. 2025. Synthetic singers: A review of deep-learning-based singing voice synthesis approaches. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the… [find](https://scholar.google.com/scholar?q=Changhao+Pan%2C+Dongyu+Yao%2C+Yu+Zhang%2C+Wenxiang+Guo%2C+Jingyu+Lu%2C+Zhiyuan+Zhu%2C+and+Zhou+Zhao%2E+2025%2E+Synthetic+singers%3A+A+review+of+deep%2Dlearning%2Dbased+singing+voice+synthesis+approaches%2E+In+Proceedings+of+)
18. Lin Huang, Chitralekha Gupta, and Haizhou Li. 2020. Spectral features and pitch histogram for automatic singing quality evaluation with CRNN. In Proc. AP-SIPA, pages 492–499. [find](https://scholar.google.com/scholar?q=Lin+Huang%2C+Chitralekha+Gupta%2C+and+Haizhou+Li%2E+2020%2E+Spectral+features+and+pitch+histogram+for+automatic+singing+quality+evaluation+with+CRNN%2E+In+Proc%2E+AP%2DSIPA%2C+pages+492%E2%80%93499%2E)
19. 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.
20. Shengpeng Ji, Yifu Chen, Minghui Fang, Jialong Zuo, Jingyu Lu, Hanting Wang, Ziyue Jiang, Long Zhou, Shujie Liu, Xize Cheng, and 1 others. 2024. Wavchat: A survey of spoken dialogue models. arXiv preprint arXiv:2411.13577. [find](https://scholar.google.com/scholar?q=Shengpeng+Ji%2C+Yifu+Chen%2C+Minghui+Fang%2C+Jialong+Zuo%2C+Jingyu+Lu%2C+Hanting+Wang%2C+Ziyue+Jiang%2C+Long+Zhou%2C+Shujie+Liu%2C+Xize+Cheng%2C+and+1+others%2E+2024%2E+Wavchat%3A+A+survey+of+spoken+dialogue+models%2E+arXiv+prep)
21. Takaaki Saeki, Detai Xin, Wataru Nakata, Tomoki Koriyama, Shinnosuke Takamichi, and Hiroshi Saruwatari. 2022. Utmos: Utokyo-sarulab system for voicemos challenge 2022. arXiv preprint arXiv:2204.02152. [find](https://scholar.google.com/scholar?q=Takaaki+Saeki%2C+Detai+Xin%2C+Wataru+Nakata%2C+Tomoki+Koriyama%2C+Shinnosuke+Takamichi%2C+and+Hiroshi+Saruwatari%2E+2022%2E+Utmos%3A+Utokyo%2Dsarulab+system+for+voicemos+challenge+2022%2E+arXiv+preprint+arXiv%3A2204%2E02152%2E)
22. Andros Tjandra, Yi-Chiao Wu, Baishan Guo, John Hoffman, Brian Ellis, Apoorv Vyas, Bowen Shi, Sanyuan Chen, Matt Le, Nick Zacharov, and 1 others. 2025. Meta audiobox aesthetics: Unified automatic quality assessment for speech, music, and sound. arXiv preprint arXiv:2502.05139. — [arXiv:2502.05139](https://arxiv.org/abs/2502.05139) [find](https://scholar.google.com/scholar?q=Andros+Tjandra%2C+Yi%2DChiao+Wu%2C+Baishan+Guo%2C+John+Hoffman%2C+Brian+Ellis%2C+Apoorv+Vyas%2C+Bowen+Shi%2C+Sanyuan+Chen%2C+Matt+Le%2C+Nick+Zacharov%2C+and+1+others%2E+2025%2E+Meta+audiobox+aesthetics%3A+Unified+automatic+quali)
23. George Tzanetakis, Andrey Ermolinskyi, and Perry Cook. 2003. Pitch histograms in audio and symbolic music information retrieval. Journal of New Music Research, pages 143–152. [find](https://scholar.google.com/scholar?q=George+Tzanetakis%2C+Andrey+Ermolinskyi%2C+and+Perry+Cook%2E+2003%2E+Pitch+histograms+in+audio+and+symbolic+music+information+retrieval%2E+Journal+of+New+Music+Research%2C+pages+143%E2%80%93152%2E)
24. Yongqi Wang, Ruofan Hu, Rongjie Huang, Zhiqing Hong, Ruiqi Li, Wenrui Liu, Fuming You, Tao Jin, and Zhou Zhao. 2024. Prompt-singer: Controllable singing-voice-synthesis with natural language prompt. arXiv preprint arXiv:2403.11780. [find](https://scholar.google.com/scholar?q=Yongqi+Wang%2C+Ruofan+Hu%2C+Rongjie+Huang%2C+Zhiqing+Hong%2C+Ruiqi+Li%2C+Wenrui+Liu%2C+Fuming+You%2C+Tao+Jin%2C+and+Zhou+Zhao%2E+2024%2E+Prompt%2Dsinger%3A+Controllable+singing%2Dvoice%2Dsynthesis+with+natural+language+prompt%2E+a)
25. Dongchao Yang, Jinchuan Tian, Xu Tan, Rongjie Huang, Songxiang Liu, Xuankai Chang, Jiatong Shi, Sheng Zhao, Jiang Bian, Xixin Wu, and 1 others. 2023. Uniaudio: An audio foundation model toward universal audio generation. arXiv preprint arXiv:2310.00704. — [arXiv:2310.00704](https://arxiv.org/abs/2310.00704) [find](https://scholar.google.com/scholar?q=Dongchao+Yang%2C+Jinchuan+Tian%2C+Xu+Tan%2C+Rongjie+Huang%2C+Songxiang+Liu%2C+Xuankai+Chang%2C+Jiatong+Shi%2C+Sheng+Zhao%2C+Jiang+Bian%2C+Xixin+Wu%2C+and+1+others%2E+2023%2E+Uniaudio%3A+An+audio+foundation+model+toward+univers)
26. Guanrou Yang, Chen Yang, Qian Chen, Ziyang Ma, Wenxi Chen, Wen Wang, Tianrui Wang, Yifan Yang, Zhikang Niu, Wenrui Liu, and 1 others. 2025. Emovoice: Llm-based emotional text-to-speech model with freestyle text prompting. arXiv preprint arXiv:2504.12867. — [arXiv:2504.12867](https://arxiv.org/abs/2504.12867) [find](https://scholar.google.com/scholar?q=Guanrou+Yang%2C+Chen+Yang%2C+Qian+Chen%2C+Ziyang+Ma%2C+Wenxi+Chen%2C+Wen+Wang%2C+Tianrui+Wang%2C+Yifan+Yang%2C+Zhikang+Niu%2C+Wenrui+Liu%2C+and+1+others%2E+2025%2E+Emovoice%3A+Llm%2Dbased+emotional+text%2Dto%2Dspeech+model+with+free)
27. Ruibin Yuan, Hanfeng Lin, Shuyue Guo, Ge Zhang, Jiahao Pan, Yongyi Zang, Haohe Liu, Yiming Liang, Wenye Ma, Xingjian Du, and 1 others. 2025. Yue: Scaling open foundation models for long-form music generation. arXiv preprint arXiv:2503.08638. — [arXiv:2503.08638](https://arxiv.org/abs/2503.08638) [find](https://scholar.google.com/scholar?q=Ruibin+Yuan%2C+Hanfeng+Lin%2C+Shuyue+Guo%2C+Ge+Zhang%2C+Jiahao+Pan%2C+Yongyi+Zang%2C+Haohe+Liu%2C+Yiming+Liang%2C+Wenye+Ma%2C+Xingjian+Du%2C+and+1+others%2E+2025%2E+Yue%3A+Scaling+open+foundation+models+for+long%2Dform+music+gen)
28. Heiga Zen, Viet Dang, Rob Clark, Yu Zhang, Ron J Weiss, Ye Jia, Zhifeng Chen, and Yonghui Wu. 2019. [Libritts: A corpus derived from librispeech for text-to-speech](https://md.research.elamur.ai/free/en/papers/zen-2019-libritts-corpus-derived-librispeech-text/). arXiv preprint arXiv:1904.02882.
29. Leying Zhang, Yao Qian, Xiaofei Wang, Manthan Thakker, Dongmei Wang, Jianwei Yu, Haibin Wu, Yuxuan Hu, Jinyu Li, Yanmin Qian, and 1 others. 2025a. Covomix2: Advancing zero-shot dialogue generation with fully non-autoregressive flow matching. arXiv preprint arXiv:2506.00885. — [arXiv:2506.00885](https://arxiv.org/abs/2506.00885) [find](https://scholar.google.com/scholar?q=Leying+Zhang%2C+Yao+Qian%2C+Xiaofei+Wang%2C+Manthan+Thakker%2C+Dongmei+Wang%2C+Jianwei+Yu%2C+Haibin+Wu%2C+Yuxuan+Hu%2C+Jinyu+Li%2C+Yanmin+Qian%2C+and+1+others%2E+2025a%2E+Covomix2%3A+Advancing+zero%2Dshot+dialogue+generation+wit)
30. Xueyao Zhang, Junan Zhang, Yuancheng Wang, Chaoren Wang, Yuanzhe Chen, Dongya Jia, Zhuo Chen, and Zhizheng Wu. 2025b. Vevo2: Bridging controllable speech and singing voice generation via unified prosody learning. arXiv preprint arXiv:2508.16332. — [arXiv:2508.16332](https://arxiv.org/abs/2508.16332) [find](https://scholar.google.com/scholar?q=Xueyao+Zhang%2C+Junan+Zhang%2C+Yuancheng+Wang%2C+Chaoren+Wang%2C+Yuanzhe+Chen%2C+Dongya+Jia%2C+Zhuo+Chen%2C+and+Zhizheng+Wu%2E+2025b%2E+Vevo2%3A+Bridging+controllable+speech+and+singing+voice+generation+via+unified+proso)
31. Yongmao Zhang, Heyang Xue, Hanzhao Li, Lei Xie, Tingwei Guo, Ruixiong Zhang, and Caixia Gong. 2022. Visinger 2: High-fidelity end-to-end singing voice synthesis enhanced by digital signal processing synthesizer. arXiv preprint arXiv:2211.02903. — [arXiv:2211.02903](https://arxiv.org/abs/2211.02903) [find](https://scholar.google.com/scholar?q=Yongmao+Zhang%2C+Heyang+Xue%2C+Hanzhao+Li%2C+Lei+Xie%2C+Tingwei+Guo%2C+Ruixiong+Zhang%2C+and+Caixia+Gong%2E+2022%2E+Visinger+2%3A+High%2Dfidelity+end%2Dto%2Dend+singing+voice+synthesis+enhanced+by+digital+signal+processing+s)
32. Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, and Zhou Zhao. 2025c. Tcsinger 2: Customizable multilingual zero-shot singing voice synthesis. arXiv preprint arXiv:2505.14910. [find](https://scholar.google.com/scholar?q=Yu+Zhang%2C+Wenxiang+Guo%2C+Changhao+Pan%2C+Dongyu+Yao%2C+Zhiyuan+Zhu%2C+Ziyue+Jiang%2C+Yuhan+Wang%2C+Tao+Jin%2C+and+Zhou+Zhao%2E+2025c%2E+Tcsinger+2%3A+Customizable+multilingual+zero%2Dshot+singing+voice+synthesis%2E+arXiv+pr)
33. Yu Zhang, Ziyue Jiang, Ruiqi Li, Changhao Pan, Jinzheng He, Rongjie Huang, Chuxin Wang, and Zhou Zhao. 2024a. Tcsinger: Zero-shot singing voice synthesis with style transfer and multi-level style control. arXiv preprint arXiv:2409.15977. [find](https://scholar.google.com/scholar?q=Yu+Zhang%2C+Ziyue+Jiang%2C+Ruiqi+Li%2C+Changhao+Pan%2C+Jinzheng+He%2C+Rongjie+Huang%2C+Chuxin+Wang%2C+and+Zhou+Zhao%2E+2024a%2E+Tcsinger%3A+Zero%2Dshot+singing+voice+synthesis+with+style+transfer+and+multi%2Dlevel+style+cont)
34. Yu Zhang, Changhao Pan, Wenxiang Guo, Ruiqi Li, Zhiyuan Zhu, Jialei Wang, Wenhao Xu, Jingyu Lu, Zhiqing Hong, Chuxin Wang, and 1 others. 2024b. Gtsinger: A global multi-technique singing corpus with realistic music scores for all singing tasks. Advances in Neural Information Processing Systems, 37:1… [find](https://scholar.google.com/scholar?q=Yu+Zhang%2C+Changhao+Pan%2C+Wenxiang+Guo%2C+Ruiqi+Li%2C+Zhiyuan+Zhu%2C+Jialei+Wang%2C+Wenhao+Xu%2C+Jingyu+Lu%2C+Zhiqing+Hong%2C+Chuxin+Wang%2C+and+1+others%2E+2024b%2E+Gtsinger%3A+A+global+multi%2Dtechnique+singing+corpus+with+r)
35. Yi Zhao, Haoyu Li, Cheng-I Lai, Jennifer Williams, Erica Cooper, and Junichi Yamagishi. 2020. Improved prosody from learned f0 codebook representations for vq-vae speech waveform reconstruction. arXiv preprint arXiv:2005.07884. — [arXiv:2005.07884](https://arxiv.org/abs/2005.07884) [find](https://scholar.google.com/scholar?q=Yi+Zhao%2C+Haoyu+Li%2C+Cheng%2DI+Lai%2C+Jennifer+Williams%2C+Erica+Cooper%2C+and+Junichi+Yamagishi%2E+2020%2E+Improved+prosody+from+learned+f0+codebook+representations+for+vq%2Dvae+speech+waveform+reconstruction%2E+arXiv)
36. Siyi Zhou, Yiquan Zhou, Yi He, Xun Zhou, Jinchao Wang, Wei Deng, and Jingchen Shu. 2025. 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+2025%2E+IndexTTS2%3A+A+Breakthrough+in+Emotionally+Expressive+and+Duration%2DControlled+Auto%2DRegressive+Zero%2DShot+Text%2Dto%2DS)

*Updated 1 November 2026*