---
title: "Comprehensive Benchmarking of Long-Form Speech Generation"
description: "Existing test sets cover few domains, and standard metrics such as WER are nearly saturated and miss long-range properties… 93 references."
authors: ["Changhao Pan", "Rui Yang", "Han Wang", "Zhuan Zhou", "Xuming He", "Wenxiang Guo", "Ziyue Jiang", "Ruiqi Li", "Yu Zhang", "Chenyuhao Wen", "Ke Lei", "Xiang Yin", "Jingyu Lu", "Zhiyuan Zhu", "Zhou Zhao"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.112/"
doi: "10.18653/v1/2026.findings-acl.112"
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/pan-2026-comprehensive-benchmarking-long-form-speech/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pan-2026-comprehensive-benchmarking-long-form-speech/)

[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/27/) / Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios

# Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios

**Authors:** [Changhao Pan](https://md.research.elamur.ai/free/en/authors/changhao-pan/), [Rui Yang](https://md.research.elamur.ai/free/en/authors/rui-yang/), [Han Wang](https://md.research.elamur.ai/free/en/authors/han-wang/), Zhuan Zhou, Xuming He, Wenxiang Guo, [Ziyue Jiang](https://md.research.elamur.ai/free/en/authors/ziyue-jiang/), Ruiqi Li, [Yu Zhang](https://md.research.elamur.ai/free/en/authors/yu-zhang/), [Chenyuhao Wen](https://md.research.elamur.ai/free/en/authors/chenyuhao-wen/), Ke Lei, Xiang Yin, [Jingyu Lu](https://md.research.elamur.ai/free/en/authors/jingyu-lu/), Zhiyuan Zhu and [Zhou Zhao](https://md.research.elamur.ai/free/en/authors/zhou-zhao/) · **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.112/) · [PDF](https://aclanthology.org/2026.findings-acl.112.pdf) · [DOI 10.18653/v1/2026.findings-acl.112](https://doi.org/10.18653/v1/2026.findings-acl.112) · [OpenAlex](https://openalex.org/W7166856290)

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

## Summary
Long-form text-to-speech has shifted from single sentences to paragraphs and multi-speaker dialogue, but evaluation has not kept pace. Existing test sets cover few domains, and standard metrics such as WER are nearly saturated and miss long-range properties like consistency and coherence. SwanBench-Speech fills this gap with a benchmark for both long-form narration and dialog generation. It is organised around three challenge axes: acoustics, semantics, and expressiveness.

The test material comes from three sources: web text, cleaned web audio, and LLM-generated scripts. The audio was denoised, filtered with DNS-MOS, diarized and transcribed. Seven automatic metrics cover the three axes, and the authors checked them against human judgments.

More than 20 open- and closed-source systems were tested. Current models roughly equal real recordings on fidelity and transcription accuracy. They still trail clearly on reverb consistency, prosodic coherence and paragraph-level expressive variation, and they are weakest in highly expressive genres. The authors link these weaknesses largely to training data: short clips, noisy web audio, and the flattening effect of scale. The benchmark gives the field a scalable, standardised way to measure long-form quality.

## Key points
- The benchmark contains 1,101 samples across 17 scenarios with 1–4 speakers each, averaging about 229 words per sample.
- The scenarios are grouped by challenge:
  - **Acoustics:** podcast, interview, audiobook, and others.
  - **Semantics:** lesson, news, seminar, and others.
  - **Expressiveness:** drama, talk show, sportscast, and others.
- The seven metrics are:
  - **Acoustics:** timbre consistency (WavLM, sliding window), reverb consistency (SRMR variability), and sound fidelity (SQUIM).
  - **Semantics:** content accuracy (CER/WER) and prosodic coherence.
  - **Expressiveness:** expressive richness and expressive hierarchy, both scored by an MLLM judge.
- Data findings for specific models:
  - SparkTTS, trained on VoxBox (segments under 10 s), degrades as texts get longer.
  - CosyVoice3, trained on in-the-wild data, lags on reverb consistency.
  - GLM-TTS and FishSpeech score well on acoustics but poorly on expressiveness.
- The authors report three limitations:
  - The benchmark covers only Chinese and English.
  - Prompt audio comes from just 20 open-source speakers.
  - Semantic evaluation of emotional and stylistic transitions is still preliminary.

*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

- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 224 works · 13,587 citations
- [ByteDance](https://md.research.elamur.ai/free/en/companies/bytedance/) — Company, Beijing, China · 47 works · 4,339 citations

📚 Shelves (4): [🖥️ 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

🧭 Topics (1): [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · 519 works

## Cite

Cite as: Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu and Zhou Zhao. 2026. Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios. 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{pan2026comprehensive,
  title = {{Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios}},
  author = {Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu and Zhou Zhao},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.112},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.112}
}
```

- [← previous Compositional Steering of Large Language Models with Steering Tokens](https://md.research.elamur.ai/free/en/papers/radevski-2026-compositional-steering-large-language-models/)
- [next → Compressed Representations of Patient Records: A Comparative Study of Template-Based and LLM-Based Methods for Clinical Data Summarization and Visualization](https://md.research.elamur.ai/free/en/papers/stockl-2026-compressed-representations-patient-records-comparative/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/27/)

## References

93 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ahmed Ali and Steve Renals. 2018. Word error rate estimation for speech recognition: e-wer. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 20–24. [find](https://scholar.google.com/scholar?q=Ahmed+Ali+and+Steve+Renals%2E+2018%2E+Word+error+rate+estimation+for+speech+recognition%3A+e%2Dwer%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+2%3A+Short+)
2. Keyu An, Qian Chen, Chong Deng, Zhihao Du, Changfeng Gao, Zhifu Gao, Yue Gu, Ting He, Hangrui Hu, Kai Hu, et al. 2024. Funaudiollm: Voice understanding and generation foundation models for natural interaction between humans and llms. arXiv preprint arXiv:2407.04051. — [arXiv:2407.04051](https://arxiv.org/abs/2407.04051) [find](https://scholar.google.com/scholar?q=Keyu+An%2C+Qian+Chen%2C+Chong+Deng%2C+Zhihao+Du%2C+Changfeng+Gao%2C+Zhifu+Gao%2C+Yue+Gu%2C+Ting+He%2C+Hangrui+Hu%2C+Kai+Hu%2C+et+al%2E+2024%2E+Funaudiollm%3A+Voice+understanding+and+generation+foundation+models+for+natural+int)
3. Philip Anastassiou, Jiawei Chen, Jitong Chen, Yuanzhe Chen, Zhuo Chen, Ziyi Chen, Jian Cong, Lelai Deng, Chuang Ding, Lu Gao, et al. 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.
4. Junyi Ao, Yuancheng Wang, Xiaohai Tian, Dekun Chen, Jun Zhang, Lu Lu, Yuxuan Wang, Haizhou Li, and Zhizheng Wu. 2024. Sd-eval: A benchmark dataset for spoken dialogue understanding beyond words. Advances in Neural Information Processing Systems, 37:56898–56918. [find](https://scholar.google.com/scholar?q=Junyi+Ao%2C+Yuancheng+Wang%2C+Xiaohai+Tian%2C+Dekun+Chen%2C+Jun+Zhang%2C+Lu+Lu%2C+Yuxuan+Wang%2C+Haizhou+Li%2C+and+Zhizheng+Wu%2E+2024%2E+Sd%2Deval%3A+A+benchmark+dataset+for+spoken+dialogue+understanding+beyond+words%2E+Advan)
5. Oleg Atamanenko, Anna Chalova, Joseph Coombes, Nikki Cope, Phillip Dang, Zhifeng Deng, Jimmy Du, Michael Ermolenko, Feifan Fan, Yufei Feng, et al. 2025. Tts-1 technical report. arXiv preprint arXiv:2507.21138. — [arXiv:2507.21138](https://arxiv.org/abs/2507.21138) [find](https://scholar.google.com/scholar?q=Oleg+Atamanenko%2C+Anna+Chalova%2C+Joseph+Coombes%2C+Nikki+Cope%2C+Phillip+Dang%2C+Zhifeng+Deng%2C+Jimmy+Du%2C+Michael+Ermolenko%2C+Feifan+Fan%2C+Yufei+Feng%2C+et+al%2E+2025%2E+Tts%2D1+technical+report%2E+arXiv+preprint+arXiv%3A25)
6. Kaito Baba, Wataru Nakata, Yuki Saito, and Hiroshi Saruwatari. 2024. The t05 system for the voicemos challenge 2024: Transfer learning from deep image classifier to naturalness mos prediction of high-quality synthetic speech. In 2024 IEEE Spoken Language Technology Workshop (SLT), pages 818–824. [find](https://scholar.google.com/scholar?q=Kaito+Baba%2C+Wataru+Nakata%2C+Yuki+Saito%2C+and+Hiroshi+Saruwatari%2E+2024%2E+The+t05+system+for+the+voicemos+challenge+2024%3A+Transfer+learning+from+deep+image+classifier+to+naturalness+mos+prediction+of+high%2D)
7. Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, et al. 2024. [Longbench: A bilingual, multitask benchmark for long context understanding](https://md.research.elamur.ai/free/en/papers/bai-2023-longbench-bilingual-multitask-benchmark/). In Proceedings of the 62nd annual meeting of the association for computational linguistic…
8. Yifu Chen, Shengpeng Ji, Haoxiao Wang, Ziqing Wang, Siyu Chen, Jinzheng He, Jin Xu, and Zhou Zhao. 2025. [Wavrag: Audio-integrated retrieval augmented generation for spoken dialogue models](https://md.research.elamur.ai/free/en/papers/chen-2025-wavrag-audio-integrated-retrieval-augmented/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
9. Yukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han, and Jiaya Jia. 2023. [Longlora: Efficient fine-tuning of long-context large language models](https://md.research.elamur.ai/free/en/papers/chen-2023-longlora-efficient-fine-tuning-long/). arXiv preprint arXiv:2309.12307.
10. Max Bain, Jaesung Huh, Tengda Han, and Andrew Zisserman. 2023. Whisperx: Time-accurate speech transcription of long-form audio. [find](https://scholar.google.com/scholar?q=Max+Bain%2C+Jaesung+Huh%2C+Tengda+Han%2C+and+Andrew+Zisserman%2E+2023%2E+Whisperx%3A+Time%2Daccurate+speech+transcription+of+long%2Dform+audio%2E)
11. Yushen Chen, Zhikang Niu, Ziyang Ma, Keqi Deng, Chunhui Wang, Jian Zhao, Kai Yu, and Xie Chen. 2024c. [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/). arXiv preprint arXiv:2410.06885.
12. Zalán Borsos, Matt Sharifi, Damien Vincent, Eugene Kharitonov, Neil Zeghidour, and Marco Tagliasacchi. 2023. Soundstorm: Efficient parallel audio generation. arXiv preprint arXiv:2305.09636. — [arXiv:2305.09636](https://arxiv.org/abs/2305.09636) [find](https://scholar.google.com/scholar?q=Zal%C3%A1n+Borsos%2C+Matt+Sharifi%2C+Damien+Vincent%2C+Eugene+Kharitonov%2C+Neil+Zeghidour%2C+and+Marco+Tagliasacchi%2E+2023%2E+Soundstorm%3A+Efficient+parallel+audio+generation%2E+arXiv+preprint+arXiv%3A2305%2E09636%2E+%E2%80%94+%5BarXiv%3A)
13. Rob Clark, Hanna Silen, Tom Kenter, and Ralph Leith. 2019. Evaluating long-form text-to-speech: Comparing the ratings of sentences and paragraphs. arXiv preprint arXiv:1909.03965. — [arXiv:1909.03965](https://arxiv.org/abs/1909.03965) [find](https://scholar.google.com/scholar?q=Rob+Clark%2C+Hanna+Silen%2C+Tom+Kenter%2C+and+Ralph+Leith%2E+2019%2E+Evaluating+long%2Dform+text%2Dto%2Dspeech%3A+Comparing+the+ratings+of+sentences+and+paragraphs%2E+arXiv+preprint+arXiv%3A1909%2E03965%2E+%E2%80%94+%5BarXiv%3A1909%2E03965%5D)
14. Julia Cambre, Jessica Colnago, Jim Maddock, Janice Tsai, and Jofish Kaye. 2020. Choice of voices: A large-scale evaluation of text-to-speech voice quality for long-form content. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. [find](https://scholar.google.com/scholar?q=Julia+Cambre%2C+Jessica+Colnago%2C+Jim+Maddock%2C+Janice+Tsai%2C+and+Jofish+Kaye%2E+2020%2E+Choice+of+voices%3A+A+large%2Dscale+evaluation+of+text%2Dto%2Dspeech+voice+quality+for+long%2Dform+content%2E+In+Proceedings+of+the+)
15. Jiayan Cui, Zhihan Yang, Naihan Li, Jiankun Tian, Xingyu Ma, Yi Zhang, Guangyu Chen, Runxuan Yang, Yuqing Cheng, Yizhi Zhou, et al. 2025. Glm-tts technical report. arXiv preprint arXiv:2512.14291. — [arXiv:2512.14291](https://arxiv.org/abs/2512.14291) [find](https://scholar.google.com/scholar?q=Jiayan+Cui%2C+Zhihan+Yang%2C+Naihan+Li%2C+Jiankun+Tian%2C+Xingyu+Ma%2C+Yi+Zhang%2C+Guangyu+Chen%2C+Runxuan+Yang%2C+Yuqing+Cheng%2C+Yizhi+Zhou%2C+et+al%2E+2025%2E+Glm%2Dtts+technical+report%2E+arXiv+preprint+arXiv%3A2512%2E14291%2E+%E2%80%94+%5B)
16. Dongping Chen, Ruoxi Chen, Shilin Zhang, Yaochen Wang, Yinuo Liu, Huichi Zhou, Qihui Zhang, Yao Wan, Pan Zhou, and Lichao Sun. 2024a. Mllm-asa-judge: Assessing multimodal llm-as-a-judge with vision-language benchmark. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Dongping+Chen%2C+Ruoxi+Chen%2C+Shilin+Zhang%2C+Yaochen+Wang%2C+Yinuo+Liu%2C+Huichi+Zhou%2C+Qihui+Zhang%2C+Yao+Wan%2C+Pan+Zhou%2C+and+Lichao+Sun%2E+2024a%2E+Mllm%2Dasa%2Djudge%3A+Assessing+multimodal+llm%2Das%2Da%2Djudge+with+vision%2Dla)
17. Zhihao Du, Changfeng Gao, Yuxuan Wang, Fan Yu, Tianyu Zhao, Hao Wang, Xiang Lv, Hui Wang, Chongjia Ni, Xian Shi, et al. 2025. Cosyvoice 3: Towards in-the-wild speech generation via scaling-up and post-training. arXiv preprint arXiv:2505.17589. — [arXiv:2505.17589](https://arxiv.org/abs/2505.17589) [find](https://scholar.google.com/scholar?q=Zhihao+Du%2C+Changfeng+Gao%2C+Yuxuan+Wang%2C+Fan+Yu%2C+Tianyu+Zhao%2C+Hao+Wang%2C+Xiang+Lv%2C+Hui+Wang%2C+Chongjia+Ni%2C+Xian+Shi%2C+et+al%2E+2025%2E+Cosyvoice+3%3A+Towards+in%2Dthe%2Dwild+speech+generation+via+scaling%2Dup+and+post)
18. Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, et al. 2021. Gigaspeech: An evolving, multi-domain asr corpus with 10,000 hours of transcribed audio. arXiv preprint arXiv:2106.06909. [find](https://scholar.google.com/scholar?q=Guoguo+Chen%2C+Shuzhou+Chai%2C+Guanbo+Wang%2C+Jiayu+Du%2C+Wei%2DQiang+Zhang%2C+Chao+Weng%2C+Dan+Su%2C+Daniel+Povey%2C+Jan+Trmal%2C+Junbo+Zhang%2C+et+al%2E+2021%2E+Gigaspeech%3A+An+evolving%2C+multi%2Ddomain+asr+corpus+with+10%2C000+ho)
19. Sanyuan Chen, Shujie Liu, Long Zhou, Yanqing Liu, Xu Tan, Jinyu Li, Sheng Zhao, Yao Qian, and Furu Wei. 2024b. Vall-e 2: Neural codec language models are human parity zero-shot text to speech synthesizers. arXiv preprint arXiv:2406.05370. — [arXiv:2406.05370](https://arxiv.org/abs/2406.05370) [find](https://scholar.google.com/scholar?q=Sanyuan+Chen%2C+Shujie+Liu%2C+Long+Zhou%2C+Yanqing+Liu%2C+Xu+Tan%2C+Jinyu+Li%2C+Sheng+Zhao%2C+Yao+Qian%2C+and+Furu+Wei%2E+2024b%2E+Vall%2De+2%3A+Neural+codec+language+models+are+human+parity+zero%2Dshot+text+to+speech+synthesi)
20. Yifu Chen, Shengpeng Ji, Qian Chen, Tianle Liang, Yangzhuo Li, Ziqing Wang, Wen Wang, Jingyu Lu, Haoxiao Wang, Xueyi Pu, Fan Zhuo, and Zhou Zhao. 2026a. Wavalign: Enhancing intelligence and expressiveness in spoken dialogue models via adaptive hybrid post-training. arXiv preprint arXiv:2604.14932. [find](https://scholar.google.com/scholar?q=Yifu+Chen%2C+Shengpeng+Ji%2C+Qian+Chen%2C+Tianle+Liang%2C+Yangzhuo+Li%2C+Ziqing+Wang%2C+Wen+Wang%2C+Jingyu+Lu%2C+Haoxiao+Wang%2C+Xueyi+Pu%2C+Fan+Zhuo%2C+and+Zhou+Zhao%2E+2026a%2E+Wavalign%3A+Enhancing+intelligence+and+expressive)
21. Yifu Chen, Shengpeng Ji, Zhengqing Liu, Qian Chen, Wen Wang, Ziqing Wang, Yangzhuo Li, Tianle Liang, and Zhou Zhao. 2026b. [Dual-axis generative reward model toward semantic and turn-taking robustness in interactive spoken dialogue models](https://md.research.elamur.ai/free/en/papers/chen-2026-dual-axis-generative-reward-model/). arXiv preprint arXiv:2604.14920.
22. Zhihao Du, Yuxuan Wang, Qian Chen, Xian Shi, Xiang Lv, Tianyu Zhao, Zhifu Gao, Yexin Yang, Changfeng Gao, Hui Wang, et al. 2024. [Cosyvoice 2: Scalable streaming speech synthesis with large language models](https://md.research.elamur.ai/free/en/papers/du-2024-cosyvoice-2-scalable-streaming-speech/). arXiv preprint arXiv:2412.10117.
23. Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Müller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et al. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning. [find](https://scholar.google.com/scholar?q=Patrick+Esser%2C+Sumith+Kulal%2C+Andreas+Blattmann%2C+Rahim+Entezari%2C+Jonas+M%C3%BCller%2C+Harry+Saini%2C+Yam+Levi%2C+Dominik+Lorenz%2C+Axel+Sauer%2C+Frederic+Boesel%2C+et+al%2E+2024%2E+Scaling+rectified+flow+transformers+for+h)
24. Zhifu Gao, Shiliang Zhang, Ian McLoughlin, and Zhijie Yan. 2022. Paraformer: Fast and accurate parallel transformer for non-autoregressive end-to-end speech recognition. arXiv preprint arXiv:2206.08317. — [arXiv:2206.08317](https://arxiv.org/abs/2206.08317) [find](https://scholar.google.com/scholar?q=Zhifu+Gao%2C+Shiliang+Zhang%2C+Ian+McLoughlin%2C+and+Zhijie+Yan%2E+2022%2E+Paraformer%3A+Fast+and+accurate+parallel+transformer+for+non%2Dautoregressive+end%2Dto%2Dend+speech+recognition%2E+arXiv+preprint+arXiv%3A2206%2E0831)
25. Google DeepMind. 2025. Gemini 3. [https://deepmind.google/technologies/gemini/](https://deepmind.google/technologies/gemini/). Accessed: 2025-12-25. [↗](https://deepmind.google/technologies/gemini/)
26. Dake Guo, Xinfa Zhu, Liumeng Xue, Yongmao Zhang, Wenjie Tian, and Lei Xie. 2024a. Text-aware and context-aware expressive audiobook speech synthesis. arXiv preprint arXiv:2406.05672. — [arXiv:2406.05672](https://arxiv.org/abs/2406.05672) [find](https://scholar.google.com/scholar?q=Dake+Guo%2C+Xinfa+Zhu%2C+Liumeng+Xue%2C+Yongmao+Zhang%2C+Wenjie+Tian%2C+and+Lei+Xie%2E+2024a%2E+Text%2Daware+and+context%2Daware+expressive+audiobook+speech+synthesis%2E+arXiv+preprint+arXiv%3A2406%2E05672%2E+%E2%80%94+%5BarXiv%3A2406%2E056)
27. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
28. Hao-Han Guo, Kun Liu, Fei-Yu Shen, Yi-Chen Wu, Feng-Long Xie, Kun Xie, and Kai-Tuo Xu. 2024b. Fireredtts: A foundation text-to-speech framework for industry-level generative speech applications. arXiv preprint arXiv:2409.03283. — [arXiv:2409.03283](https://arxiv.org/abs/2409.03283) [find](https://scholar.google.com/scholar?q=Hao%2DHan+Guo%2C+Kun+Liu%2C+Fei%2DYu+Shen%2C+Yi%2DChen+Wu%2C+Feng%2DLong+Xie%2C+Kun+Xie%2C+and+Kai%2DTuo+Xu%2E+2024b%2E+Fireredtts%3A+A+foundation+text%2Dto%2Dspeech+framework+for+industry%2Dlevel+generative+speech+applications%2E+arXiv)
29. Haorui He, Zengqiang Shang, Chaoren Wang, Xuyuan Li, Yicheng Gu, Hua Hua, Liwei Liu, Chen Yang, Jiaqi Li, Peiyang Shi, et al. 2024. Emilia: An extensive, multilingual, and diverse speech dataset for large-scale speech generation. In 2024 IEEE Spoken Language Technology Workshop (SLT), pages 885– 890… [find](https://scholar.google.com/scholar?q=Haorui+He%2C+Zengqiang+Shang%2C+Chaoren+Wang%2C+Xuyuan+Li%2C+Yicheng+Gu%2C+Hua+Hua%2C+Liwei+Liu%2C+Chen+Yang%2C+Jiaqi+Li%2C+Peiyang+Shi%2C+et+al%2E+2024%2E+Emilia%3A+An+extensive%2C+multilingual%2C+and+diverse+speech+dataset+for+l)
30. Kexin Huang, Qian Tu, Liwei Fan, Chenchen Yang, Dong Zhang, Shimin Li, Zhaoye Fei, Qinyuan Cheng, and Xipeng Qiu. 2025. Instructttseval: Benchmarking complex natural-language instruction following in text-to-speech systems. arXiv preprint arXiv:2506.16381. [find](https://scholar.google.com/scholar?q=Kexin+Huang%2C+Qian+Tu%2C+Liwei+Fan%2C+Chenchen+Yang%2C+Dong+Zhang%2C+Shimin+Li%2C+Zhaoye+Fei%2C+Qinyuan+Cheng%2C+and+Xipeng+Qiu%2E+2025%2E+Instructttseval%3A+Benchmarking+complex+natural%2Dlanguage+instruction+following+in+)
31. ZHAO Huijuan, YE Ning, and WANG Ruchuan. 2023. Improved cross-corpus speech emotion recognition using deep local domain adaptation. Chinese Journal of Electronics, 32(3):640–646. [find](https://scholar.google.com/scholar?q=ZHAO+Huijuan%2C+YE+Ning%2C+and+WANG+Ruchuan%2E+2023%2E+Improved+cross%2Dcorpus+speech+emotion+recognition+using+deep+local+domain+adaptation%2E+Chinese+Journal+of+Electronics%2C+32%283%29%3A640%E2%80%93646%2E)
32. Hieu-Nghia Huynh-Nguyen, Ngoc Son Nguyen, Huynh Nguyen Dang, Thieu Vo, Truong-Son Hy, and Van Nguyen. 2025. Ozspeech: One-step zero-shot speech synthesis with learned-prior-conditioned flow matching. arXiv preprint arXiv:2505.12800. [find](https://scholar.google.com/scholar?q=Hieu%2DNghia+Huynh%2DNguyen%2C+Ngoc+Son+Nguyen%2C+Huynh+Nguyen+Dang%2C+Thieu+Vo%2C+Truong%2DSon+Hy%2C+and+Van+Nguyen%2E+2025%2E+Ozspeech%3A+One%2Dstep+zero%2Dshot+speech+synthesis+with+learned%2Dprior%2Dconditioned+flow+matching%2E+)
33. Shengpeng Ji, Yifu Chen, Minghui Fang, Jialong Zuo, Jingyu Lu, Hanting Wang, Ziyue Jiang, Long Zhou, Shujie Liu, Xize Cheng, Xiaoda Yang, Zehan Wang, Qian Yang, Jian Li, Jingzhen Jiang, Yidi ang He, Yunfei Chu, Jin Xu, and Zhou Zhao. 2024a. Wavchat: A survey of spoken dialogue models. arXiv preprint… [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+Xiaoda+Yang%2C+Zehan+Wang%2C+Qian+Yang%2C+Jian+Li%2C+Jingzhen+Jiang%2C+Yidi+ang+He%2C+Y)
34. Shengpeng Ji, Ziyue Jiang, Wen Wang, Yifu Chen, Minghui Fang, Jialong Zuo, Qian Yang, Xize Cheng, Zehan Wang, Ruiqi Li, et al. 2024b. Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling. arXiv preprint arXiv:2408.16532. — [arXiv:2408.16532](https://arxiv.org/abs/2408.16532) [find](https://scholar.google.com/scholar?q=Shengpeng+Ji%2C+Ziyue+Jiang%2C+Wen+Wang%2C+Yifu+Chen%2C+Minghui+Fang%2C+Jialong+Zuo%2C+Qian+Yang%2C+Xize+Cheng%2C+Zehan+Wang%2C+Ruiqi+Li%2C+et+al%2E+2024b%2E+Wavtokenizer%3A+an+efficient+acoustic+discrete+codec+tokenizer+for+a)
35. Ziyue Jiang, Yi Ren, Ruiqi Li, Shengpeng Ji, Boyang Zhang, Zhenhui Ye, Chen Zhang, Bai Jionghao, Xiaoda Yang, Jialong Zuo, et al. 2025. Megatts 3: Sparse alignment enhanced latent diffusion transformer for zero-shot speech synthesis. arXiv preprint arXiv:2502.18924. — [arXiv:2502.18924](https://arxiv.org/abs/2502.18924) [find](https://scholar.google.com/scholar?q=Ziyue+Jiang%2C+Yi+Ren%2C+Ruiqi+Li%2C+Shengpeng+Ji%2C+Boyang+Zhang%2C+Zhenhui+Ye%2C+Chen+Zhang%2C+Bai+Jionghao%2C+Xiaoda+Yang%2C+Jialong+Zuo%2C+et+al%2E+2025%2E+Megatts+3%3A+Sparse+alignment+enhanced+latent+diffusion+transforme)
36. Zeqian Ju, Yuancheng Wang, Kai Shen, Xu Tan, Detai Xin, Dongchao Yang, Yanqing Liu, Yichong Leng, Kaitao Song, Siliang Tang, et al. 2024. Naturalspeech 3: zero-shot speech synthesis with factorized codec and diffusion models. In Proceedings of the 41st International Conference on Machine Learning, p… [find](https://scholar.google.com/scholar?q=Zeqian+Ju%2C+Yuancheng+Wang%2C+Kai+Shen%2C+Xu+Tan%2C+Detai+Xin%2C+Dongchao+Yang%2C+Yanqing+Liu%2C+Yichong+Leng%2C+Kaitao+Song%2C+Siliang+Tang%2C+et+al%2E+2024%2E+Naturalspeech+3%3A+zero%2Dshot+speech+synthesis+with+factorized+co)
37. Zeqian Ju, Dongchao Yang, Jianwei Yu, Kai Shen, Yichong Leng, Zhengtao Wang, Xu Tan, Xinyu Zhou, Tao Qin, and Xiangyang Li. 2025. Mooncast: High-quality zero-shot podcast generation. arXiv preprint arXiv:2503.14345. — [arXiv:2503.14345](https://arxiv.org/abs/2503.14345) [find](https://scholar.google.com/scholar?q=Zeqian+Ju%2C+Dongchao+Yang%2C+Jianwei+Yu%2C+Kai+Shen%2C+Yichong+Leng%2C+Zhengtao+Wang%2C+Xu+Tan%2C+Xinyu+Zhou%2C+Tao+Qin%2C+and+Xiangyang+Li%2E+2025%2E+Mooncast%3A+High%2Dquality+zero%2Dshot+podcast+generation%2E+arXiv+preprint+ar)
38. Eugene Kharitonov, Damien Vincent, Zalán Borsos, Raphaël Marinier, Sertan Girgin, Olivier Pietquin, Matt Sharifi, Marco Tagliasacchi, and Neil Zeghidour. 2023. [Speak, read and prompt: High-fidelity text-to-speech with minimal supervision](https://md.research.elamur.ai/free/en/papers/kharitonov-2023-speak-read-prompt-high-fidelity/). Transactions of the Association for Computational Linguistics…
39. Diederik P Kingma, Max Welling, et al. 2013. Autoencoding variational bayes. [find](https://scholar.google.com/scholar?q=Diederik+P+Kingma%2C+Max+Welling%2C+et+al%2E+2013%2E+Autoencoding+variational+bayes%2E)
40. Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Michiel Bacchiani, Yu Zhang, Wei Han, and Ankur Bapna. 2023. Libritts-r: A restored multi-speaker text-to-speech corpus. arXiv preprint arXiv:2305.18802. — [arXiv:2305.18802](https://arxiv.org/abs/2305.18802) [find](https://scholar.google.com/scholar?q=Yuma+Koizumi%2C+Heiga+Zen%2C+Shigeki+Karita%2C+Yifan+Ding%2C+Kohei+Yatabe%2C+Nobuyuki+Morioka%2C+Michiel+Bacchiani%2C+Yu+Zhang%2C+Wei+Han%2C+and+Ankur+Bapna%2E+2023%2E+Libritts%2Dr%3A+A+restored+multi%2Dspeaker+text%2Dto%2Dspeech+co)
41. Anurag Kumar, Ke Tan, Zhaoheng Ni, Pranay Manocha, Xiaohui Zhang, Ethan Henderson, and Buye Xu. 2023. Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pag… [find](https://scholar.google.com/scholar?q=Anurag+Kumar%2C+Ke+Tan%2C+Zhaoheng+Ni%2C+Pranay+Manocha%2C+Xiaohui+Zhang%2C+Ethan+Henderson%2C+and+Buye+Xu%2E+2023%2E+Torchaudio%2Dsquim%3A+Reference%2Dless+speech+quality+and+intelligibility+measures+in+torchaudio%2E+In+ICA)
42. Matthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Leda Sari, Rashel Moritz, Mary Williamson, Vimal Manohar, Yossi Adi, Jay Mahadeokar, et al. 2023. Voicebox: Text-guided multilingual universal speech generation at scale. Advances in neural information processing systems, 36:14005–14034. [find](https://scholar.google.com/scholar?q=Matthew+Le%2C+Apoorv+Vyas%2C+Bowen+Shi%2C+Brian+Karrer%2C+Leda+Sari%2C+Rashel+Moritz%2C+Mary+Williamson%2C+Vimal+Manohar%2C+Yossi+Adi%2C+Jay+Mahadeokar%2C+et+al%2E+2023%2E+Voicebox%3A+Text%2Dguided+multilingual+universal+speech+)
43. Yinghao Aaron Li, Cong Han, Vinay Raghavan, Gavin Mischler, and Nima Mesgarani. 2024. Styletts 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Yinghao+Aaron+Li%2C+Cong+Han%2C+Vinay+Raghavan%2C+Gavin+Mischler%2C+and+Nima+Mesgarani%2E+2024%2E+Styletts+2%3A+Towards+human%2Dlevel+text%2Dto%2Dspeech+through+style+diffusion+and+adversarial+training+with+large+speech+)
44. Zhipeng Li, Xiaofen Xing, Jingyuan Xing, Hangrui Hu, Heng Lu, and Xiangmin Xu. 2025. Long-context speech synthesis with context-aware memory. arXiv preprint arXiv:2508.14713. — [arXiv:2508.14713](https://arxiv.org/abs/2508.14713) [find](https://scholar.google.com/scholar?q=Zhipeng+Li%2C+Xiaofen+Xing%2C+Jingyuan+Xing%2C+Hangrui+Hu%2C+Heng+Lu%2C+and+Xiangmin+Xu%2E+2025%2E+Long%2Dcontext+speech+synthesis+with+context%2Daware+memory%2E+arXiv+preprint+arXiv%3A2508%2E14713%2E+%E2%80%94+%5BarXiv%3A2508%2E14713%5D%28http)
45. 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)
46. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. 2024a. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+et+al%2E+2024a%2E+Deepseek%2Dv3+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E19437)
47. Rui Liu, Yifan Hu, Yi Ren, Xiang Yin, and Haizhou Li. 2024b. Generative expressive conversational speech synthesis. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 4187–4196. [find](https://scholar.google.com/scholar?q=Rui+Liu%2C+Yifan+Hu%2C+Yi+Ren%2C+Xiang+Yin%2C+and+Haizhou+Li%2E+2024b%2E+Generative+expressive+conversational+speech+synthesis%2E+In+Proceedings+of+the+32nd+ACM+International+Conference+on+Multimedia%2C+pages+4187%E2%80%9341)
48. Se Jin Park, Julian Salazar, Aren Jansen, Keisuke Kinoshita, Yong Man Ro, and RJ Skerry-Ryan. 2024. Long-form speech generation with spoken language models. arXiv preprint arXiv:2412.18603. — [arXiv:2412.18603](https://arxiv.org/abs/2412.18603) [find](https://scholar.google.com/scholar?q=Se+Jin+Park%2C+Julian+Salazar%2C+Aren+Jansen%2C+Keisuke+Kinoshita%2C+Yong+Man+Ro%2C+and+RJ+Skerry%2DRyan%2E+2024%2E+Long%2Dform+speech+generation+with+spoken+language+models%2E+arXiv+preprint+arXiv%3A2412%2E18603%2E+%E2%80%94+%5BarXiv%3A2)
49. LIN Long and TAN Liang. 2022. Multi-distributed speech emotion recognition based on mel frequency cepstogram and parameter transfer. Chinese Journal of Electronics, 31(1):155–167. [find](https://scholar.google.com/scholar?q=LIN+Long+and+TAN+Liang%2E+2022%2E+Multi%2Ddistributed+speech+emotion+recognition+based+on+mel+frequency+cepstogram+and+parameter+transfer%2E+Chinese+Journal+of+Electronics%2C+31%281%29%3A155%E2%80%93167%2E)
50. Zhiliang Peng, Jianwei Yu, Wenhui Wang, Yaoyao Chang, Yutao Sun, Li Dong, Yi Zhu, Weijiang Xu, Hangbo Bao, Zehua Wang, et al. 2025. Vibevoice technical report. arXiv preprint arXiv:2508.19205. — [arXiv:2508.19205](https://arxiv.org/abs/2508.19205) [find](https://scholar.google.com/scholar?q=Zhiliang+Peng%2C+Jianwei+Yu%2C+Wenhui+Wang%2C+Yaoyao+Chang%2C+Yutao+Sun%2C+Li+Dong%2C+Yi+Zhu%2C+Weijiang+Xu%2C+Hangbo+Bao%2C+Zehua+Wang%2C+et+al%2E+2025%2E+Vibevoice+technical+report%2E+arXiv+preprint+arXiv%3A2508%2E19205%2E+%E2%80%94+%5BarXi)
51. Ruskin Raj Manku, Yuzhi Tang, Xingjian Shi, Mu Li, and Alex Smola. 2025. Emergenttts-eval: Evaluating tts models on complex prosodic, expressiveness, and linguistic challenges using model-as-a-judge. arXiv preprint arXiv:2505.23009. — [arXiv:2505.23009](https://arxiv.org/abs/2505.23009) [find](https://scholar.google.com/scholar?q=Ruskin+Raj+Manku%2C+Yuzhi+Tang%2C+Xingjian+Shi%2C+Mu+Li%2C+and+Alex+Smola%2E+2025%2E+Emergenttts%2Deval%3A+Evaluating+tts+models+on+complex+prosodic%2C+expressiveness%2C+and+linguistic+challenges+using+model%2Das%2Da%2Djudge%2E+)
52. Chandan KA Reddy, Vishak Gopal, and Ross Cutler. 2021. Dnsmos: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 6493–6497. [find](https://scholar.google.com/scholar?q=Chandan+KA+Reddy%2C+Vishak+Gopal%2C+and+Ross+Cutler%2E+2021%2E+Dnsmos%3A+A+non%2Dintrusive+perceptual+objective+speech+quality+metric+to+evaluate+noise+suppressors%2E+In+ICASSP+2021%2D2021+IEEE+International+Conferen)
53. Luz Martinez-Lucas, Mohammed Abdelwahab, and Carlos Busso. 2020. The msp-conversation corpus. [find](https://scholar.google.com/scholar?q=Luz+Martinez%2DLucas%2C+Mohammed+Abdelwahab%2C+and+Carlos+Busso%2E+2020%2E+The+msp%2Dconversation+corpus%2E)
54. Michael McAuliffe, Michaela Socolof, Sarah Mihuc, Michael Wagner, and Morgan Sonderegger. 2017. Montreal forced aligner: Trainable text-speech alignment using kaldi. In Interspeech, volume 2017, pages 498–502. [find](https://scholar.google.com/scholar?q=Michael+McAuliffe%2C+Michaela+Socolof%2C+Sarah+Mihuc%2C+Michael+Wagner%2C+and+Morgan+Sonderegger%2E+2017%2E+Montreal+forced+aligner%3A+Trainable+text%2Dspeech+alignment+using+kaldi%2E+In+Interspeech%2C+volume+2017%2C+pages)
55. Christoph Minixhofer, Ondřej Klejch, and Peter Bell. 2024. Ttsds-text-to-speech distribution score. In 2024 IEEE Spoken Language Technology Workshop (SLT), pages 766–773. [find](https://scholar.google.com/scholar?q=Christoph+Minixhofer%2C+Ondr%CC%8Cej+Klejch%2C+and+Peter+Bell%2E+2024%2E+Ttsds%2Dtext%2Dto%2Dspeech+distribution+score%2E+In+2024+IEEE+Spoken+Language+Technology+Workshop+%28SLT%29%2C+pages+766%E2%80%93773%2E)
56. Christoph Minixhofer, Ondrej Klejch, and Peter Bell. 2025. Ttsds2: Resources and benchmark for evaluating human-quality text to speech systems. arXiv preprint arXiv:2506.19441. — [arXiv:2506.19441](https://arxiv.org/abs/2506.19441) [find](https://scholar.google.com/scholar?q=Christoph+Minixhofer%2C+Ondrej+Klejch%2C+and+Peter+Bell%2E+2025%2E+Ttsds2%3A+Resources+and+benchmark+for+evaluating+human%2Dquality+text+to+speech+systems%2E+arXiv+preprint+arXiv%3A2506%2E19441%2E+%E2%80%94+%5BarXiv%3A2506%2E19441%5D%28ht)
57. Yuto Nishimura, Takumi Hirose, Masanari Ohi, Hideki Nakayama, and Nakamasa Inoue. 2024. Hall-e: hierarchical neural codec language model for minute-long zero-shot text-to-speech synthesis. arXiv preprint arXiv:2410.04380. — [arXiv:2410.04380](https://arxiv.org/abs/2410.04380) [find](https://scholar.google.com/scholar?q=Yuto+Nishimura%2C+Takumi+Hirose%2C+Masanari+Ohi%2C+Hideki+Nakayama%2C+and+Nakamasa+Inoue%2E+2024%2E+Hall%2De%3A+hierarchical+neural+codec+language+model+for+minute%2Dlong+zero%2Dshot+text%2Dto%2Dspeech+synthesis%2E+arXiv+prepr)
58. OpenAI. 2024. Video generation models as world [https://openai.com/index/](https://openai.com/index/) simulators. video-generation-models-as-world-simulators/. Accessed: 2025-12-25. [↗](https://openai.com/index/)
59. OpenAI. 2025. Gpt-5. [https://chagpt.com/](https://chagpt.com/). Accessed: 2025-12-25. [↗](https://chagpt.com/)
60. 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+)
61. Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. 2015. Librispeech: an asr corpus based on public domain audio books. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pages 5206–5210. IEEE. [find](https://scholar.google.com/scholar?q=Vassil+Panayotov%2C+Guoguo+Chen%2C+Daniel+Povey%2C+and+Sanjeev+Khudanpur%2E+2015%2E+Librispeech%3A+an+asr+corpus+based+on+public+domain+audio+books%2E+In+2015+IEEE+international+conference+on+acoustics%2C+speech+and+)
62. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). arXiv preprint arXiv:1908.10084.
63. Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2020. Fastspeech 2: Fast and high-quality end-to-end text to speech. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yi+Ren%2C+Chenxu+Hu%2C+Xu+Tan%2C+Tao+Qin%2C+Sheng+Zhao%2C+Zhou+Zhao%2C+and+Tie%2DYan+Liu%2E+2020%2E+Fastspeech+2%3A+Fast+and+high%2Dquality+end%2Dto%2Dend+text+to+speech%2E+In+International+Conference+on+Learning+Representations)
64. Takaaki Saeki, Detai Xin, Wataru Nakata, Tomoki Koriyama, Shinnosuke Takamichi, and Hiroshi Saruwatari. 2022. [Utmos: Utokyo-sarulab system for voicemos challenge 2022](https://md.research.elamur.ai/free/en/papers/saeki-2022-utmos-utokyo-sarulab-system-voicemos/). arXiv preprint arXiv:2204.02152.
65. Kai Shen, Zeqian Ju, Xu Tan, Eric Liu, Yichong Leng, Lei He, Tao Qin, Sheng Zhao, and Jiang Bian. 2024. Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers. In ICLR. [find](https://scholar.google.com/scholar?q=Kai+Shen%2C+Zeqian+Ju%2C+Xu+Tan%2C+Eric+Liu%2C+Yichong+Leng%2C+Lei+He%2C+Tao+Qin%2C+Sheng+Zhao%2C+and+Jiang+Bian%2E+2024%2E+Naturalspeech+2%3A+Latent+diffusion+models+are+natural+and+zero%2Dshot+speech+and+singing+synthesize)
66. Yao Shi, Hui Bu, Xin Xu, Shaoji Zhang, and Ming Li. 2020. Aishell-3: A multi-speaker mandarin tts corpus and the baselines. arXiv preprint arXiv:2010.11567. [find](https://scholar.google.com/scholar?q=Yao+Shi%2C+Hui+Bu%2C+Xin+Xu%2C+Shaoji+Zhang%2C+and+Ming+Li%2E+2020%2E+Aishell%2D3%3A+A+multi%2Dspeaker+mandarin+tts+corpus+and+the+baselines%2E+arXiv+preprint+arXiv%3A2010%2E11567%2E)
67. Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Koluguri, Piotr Żelasko, Somshubra Majumdar, Adel Moumen, and Sanchit Gandhi. 2025. Open asr leaderboard: Towards reproducible and transparent multilingual and long-form speech recognition evaluation. arXiv preprint arXiv:2510.… — [arXiv:2510.06961](https://arxiv.org/abs/2510.06961) [find](https://scholar.google.com/scholar?q=Vaibhav+Srivastav%2C+Steven+Zheng%2C+Eric+Bezzam%2C+Eustache+Le+Bihan%2C+Nithin+Koluguri%2C+Piotr+Z%CC%87elasko%2C+Somshubra+Majumdar%2C+Adel+Moumen%2C+and+Sanchit+Gandhi%2E+2025%2E+Open+asr+leaderboard%3A+Towards+reproducible+)
68. Cees H Taal, Richard C Hendriks, Richard Heusdens, and Jesper Jensen. 2010. A short-time objective intelligibility measure for time-frequency weighted noisy speech. In IEEE international conference on acoustics, speech and signal processing. [find](https://scholar.google.com/scholar?q=Cees+H+Taal%2C+Richard+C+Hendriks%2C+Richard+Heusdens%2C+and+Jesper+Jensen%2E+2010%2E+A+short%2Dtime+objective+intelligibility+measure+for+time%2Dfrequency+weighted+noisy+speech%2E+In+IEEE+international+conference+on)
69. Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang, Haoyang Zhang, Yuxin Li, Daijiao Liu, Yayue Deng, Donghang Wu, Jun Chen, Liang Zhao, et al. 2025. [Step-audio-r1 technical report](https://md.research.elamur.ai/free/en/papers/tian-2025-step-audio-r1-technical/). arXiv preprint arXiv:2511.15848.
70. Haoxu Wang and Biao Tian. 2025. Zipenhancer: Dual-path down-up sampling-based zipformer for monaural speech enhancement. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. [find](https://scholar.google.com/scholar?q=Haoxu+Wang+and+Biao+Tian%2E+2025%2E+Zipenhancer%3A+Dual%2Dpath+down%2Dup+sampling%2Dbased+zipformer+for+monaural+speech+enhancement%2E+In+ICASSP+2025%2D2025+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Sign)
71. Weicheng Zhang, Cheng-Chieh Yeh, Will Beckman, Tuomo Raitio, Ramya Rasipuram, Ladan Golipour, and David Winarsky. 2023. Audiobook synthesis with long-form neural text-to-speech. In 12th Speech Synthesis Workshop (SSW) 2023. [find](https://scholar.google.com/scholar?q=Weicheng+Zhang%2C+Cheng%2DChieh+Yeh%2C+Will+Beckman%2C+Tuomo+Raitio%2C+Ramya+Rasipuram%2C+Ladan+Golipour%2C+and+David+Winarsky%2E+2023%2E+Audiobook+synthesis+with+long%2Dform+neural+text%2Dto%2Dspeech%2E+In+12th+Speech+Synthes)
72. Xin Wang, Yudong Chen, and Wenwu Zhu. 2021. A survey on curriculum learning. IEEE transactions on pattern analysis and machine intelligence, pages 4555–4576. [find](https://scholar.google.com/scholar?q=Xin+Wang%2C+Yudong+Chen%2C+and+Wenwu+Zhu%2E+2021%2E+A+survey+on+curriculum+learning%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence%2C+pages+4555%E2%80%934576%2E)
73. Xueyao Zhang, Chaoren Wang, Huan Liao, Ziniu Li, Yuancheng Wang, Li Wang, Dongya Jia, Yuanzhe Chen, Xiulin Li, Zhuo Chen, et al. 2025b. Speechjudge: Towards human-level judgment for speech naturalness. arXiv preprint arXiv:2511.07931. — [arXiv:2511.07931](https://arxiv.org/abs/2511.07931) [find](https://scholar.google.com/scholar?q=Xueyao+Zhang%2C+Chaoren+Wang%2C+Huan+Liao%2C+Ziniu+Li%2C+Yuancheng+Wang%2C+Li+Wang%2C+Dongya+Jia%2C+Yuanzhe+Chen%2C+Xiulin+Li%2C+Zhuo+Chen%2C+et+al%2E+2025b%2E+Speechjudge%3A+Towards+human%2Dlevel+judgment+for+speech+naturalness)
74. Xinsheng Wang, Mingqi Jiang, Ziyang Ma, Ziyu Zhang, Songxiang Liu, Linqin Li, Zheng Liang, Qixi Zheng, Rui Wang, Xiaoqin Feng, et al. 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+et+al%2E+2025%2E+Spark%2Dtts%3A+An+efficient+llm%2Dbased+text%2Dto%2Dspeech+model+with+)
75. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems.
76. Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453. [find](https://scholar.google.com/scholar?q=Guangxuan+Xiao%2C+Yuandong+Tian%2C+Beidi+Chen%2C+Song+Han%2C+and+Mike+Lewis%2E+2023%2E+Efficient+streaming+language+models+with+attention+sinks%2E+arXiv+preprint+arXiv%3A2309%2E17453%2E)
77. Hanke Xie, Haopeng Lin, Wenxiao Cao, Dake Guo, Wenjie Tian, Jun Wu, Hanlin Wen, Ruixuan Shang, Hongmei Liu, Zhiqi Jiang, et al. 2025a. Soulx-podcast: Towards realistic long-form podcasts with dialectal and paralinguistic diversity. arXiv preprint arXiv:2510.23541. — [arXiv:2510.23541](https://arxiv.org/abs/2510.23541) [find](https://scholar.google.com/scholar?q=Hanke+Xie%2C+Haopeng+Lin%2C+Wenxiao+Cao%2C+Dake+Guo%2C+Wenjie+Tian%2C+Jun+Wu%2C+Hanlin+Wen%2C+Ruixuan+Shang%2C+Hongmei+Liu%2C+Zhiqi+Jiang%2C+et+al%2E+2025a%2E+Soulx%2Dpodcast%3A+Towards+realistic+long%2Dform+podcasts+with+dialecta)
78. Kun Xie, Feiyu Shen, Junjie Li, Fenglong Xie, Xu Tang, and Yao Hu. 2025b. Fireredtts-2: Towards long conversational speech generation for podcast and chatbot. arXiv preprint arXiv:2509.02020. — [arXiv:2509.02020](https://arxiv.org/abs/2509.02020) [find](https://scholar.google.com/scholar?q=Kun+Xie%2C+Feiyu+Shen%2C+Junjie+Li%2C+Fenglong+Xie%2C+Xu+Tang%2C+and+Yao+Hu%2E+2025b%2E+Fireredtts%2D2%3A+Towards+long+conversational+speech+generation+for+podcast+and+chatbot%2E+arXiv+preprint+arXiv%3A2509%2E02020%2E+%E2%80%94+%5BarXiv)
79. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, et al. 2025a. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215. — [Qwen2.5-Omni Technical Report](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen2-5-omni-technical/)
80. Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, et al. 2025b. [Qwen3-omni technical report](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen3-omni-technical-report/). arXiv preprint arXiv:2509.17765.
81. Binbin Zhang, Hang Lv, Pengcheng Guo, Qijie Shao, Chao Yang, Lei Xie, Xin Xu, Hui Bu, Xiaoyu Chen, Chenchen Zeng, et al. 2022. Wenetspeech: A 10000+ hours multi-domain mandarin corpus for speech recognition. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing… [find](https://scholar.google.com/scholar?q=Binbin+Zhang%2C+Hang+Lv%2C+Pengcheng+Guo%2C+Qijie+Shao%2C+Chao+Yang%2C+Lei+Xie%2C+Xin+Xu%2C+Hui+Bu%2C+Xiaoyu+Chen%2C+Chenchen+Zeng%2C+et+al%2E+2022%2E+Wenetspeech%3A+A+10000%2B+hours+multi%2Ddomain+mandarin+corpus+for+speech+recog)
82. Bowen Zhang, Congchao Guo, Geng Yang, Hang Yu, Haozhe Zhang, Heidi Lei, Jialong Mai, Junjie Yan, Kaiyue Yang, Mingqi Yang, et al. 2025a. Minimax-speech: Intrinsic zero-shot text-to-speech with a learnable speaker encoder. arXiv preprint arXiv:2505.07916. — [arXiv:2505.07916](https://arxiv.org/abs/2505.07916) [find](https://scholar.google.com/scholar?q=Bowen+Zhang%2C+Congchao+Guo%2C+Geng+Yang%2C+Hang+Yu%2C+Haozhe+Zhang%2C+Heidi+Lei%2C+Jialong+Mai%2C+Junjie+Yan%2C+Kaiyue+Yang%2C+Mingqi+Yang%2C+et+al%2E+2025a%2E+Minimax%2Dspeech%3A+Intrinsic+zero%2Dshot+text%2Dto%2Dspeech+with+a+learn)
83. 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)
84. Yu Zhang, Wenxiang Guo, Changhao Pan, Zhiyuan Zhu, Tao Jin, and Zhou Zhao. 2025d. Isdrama: Immersive spatial drama generation through multimodal prompting. In Proceedings of the 33rd ACM International Conference on Multimedia. [find](https://scholar.google.com/scholar?q=Yu+Zhang%2C+Wenxiang+Guo%2C+Changhao+Pan%2C+Zhiyuan+Zhu%2C+Tao+Jin%2C+and+Zhou+Zhao%2E+2025d%2E+Isdrama%3A+Immersive+spatial+drama+generation+through+multimodal+prompting%2E+In+Proceedings+of+the+33rd+ACM+International)
85. Yu Zhang, Rongjie Huang, Ruiqi Li, JinZheng He, Yan Xia, Feiyang Chen, Xinyu Duan, Baoxing Huai, and Zhou Zhao. 2024a. Stylesinger: Style transfer for out-of-domain singing voice synthesis. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19597–19605. [find](https://scholar.google.com/scholar?q=Yu+Zhang%2C+Rongjie+Huang%2C+Ruiqi+Li%2C+JinZheng+He%2C+Yan+Xia%2C+Feiyang+Chen%2C+Xinyu+Duan%2C+Baoxing+Huai%2C+and+Zhou+Zhao%2E+2024a%2E+Stylesinger%3A+Style+transfer+for+out%2Dof%2Ddomain+singing+voice+synthesis%2E+In+Proceed)
86. Yu Zhang, Ziyue Jiang, Ruiqi Li, Changhao Pan, Jinzheng He, Rongjie Huang, Chuxin Wang, and Zhou Zhao. 2024b. Tcsinger: Zero-shot singing voice synthesis with style transfer and multi-level style control. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, page… [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+2024b%2E+Tcsinger%3A+Zero%2Dshot+singing+voice+synthesis+with+style+transfer+and+multi%2Dlevel+style+cont)
87. Yu Zhang, Changhao Pan, Wenxiang Guo, Ruiqi Li, Zhiyuan Zhu, Jialei Wang, Wenhao Xu, Jingyu Lu, Zhiqing Hong, Chuxin Wang, et al. 2024c. Gtsinger: A global multi-technique singing corpus with realistic music scores for all singing tasks. In The Thirty-eight Conference on Neural Information Processin… [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+et+al%2E+2024c%2E+Gtsinger%3A+A+global+multi%2Dtechnique+singing+corpus+with+realisti)
88. Xingjian Zhao, Zhe Xu, Qinyuan Cheng, Zhaoye Fei, Luozhijie Jin, Yang Wang, Hanfu Chen, Yaozhou Jiang, Qinghui Gao, Ke Chen, et al. 2025. Moss-speech: Towards true speech-to-speech models without text guidance. arXiv preprint arXiv:2510.00499. — [arXiv:2510.00499](https://arxiv.org/abs/2510.00499) [find](https://scholar.google.com/scholar?q=Xingjian+Zhao%2C+Zhe+Xu%2C+Qinyuan+Cheng%2C+Zhaoye+Fei%2C+Luozhijie+Jin%2C+Yang+Wang%2C+Hanfu+Chen%2C+Yaozhou+Jiang%2C+Qinghui+Gao%2C+Ke+Chen%2C+et+al%2E+2025%2E+Moss%2Dspeech%3A+Towards+true+speech%2Dto%2Dspeech+models+without+text)
89. Siqi Zheng, Luyao Cheng, Yafeng Chen, Hui Wang, and Qian Chen. 2023. 3d-speaker: A large-scale multi-device, multi-distance, and multi-dialect corpus for speech representation disentanglement. arXiv preprint arXiv:2306.15354. — [arXiv:2306.15354](https://arxiv.org/abs/2306.15354) [find](https://scholar.google.com/scholar?q=Siqi+Zheng%2C+Luyao+Cheng%2C+Yafeng+Chen%2C+Hui+Wang%2C+and+Qian+Chen%2E+2023%2E+3d%2Dspeaker%3A+A+large%2Dscale+multi%2Ddevice%2C+multi%2Ddistance%2C+and+multi%2Ddialect+corpus+for+speech+representation+disentanglement%2E+arXiv+p)
90. Jiaming Zhou, Shiyao Wang, Shiwan Zhao, Jiabei He, Haoqin Sun, Hui Wang, Cheng Liu, Aobo Kong, Yujie Guo, Xi Yang, et al. 2025a. Childmandarin: A comprehensive mandarin speech dataset for young children aged 3-5. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguist… [find](https://scholar.google.com/scholar?q=Jiaming+Zhou%2C+Shiyao+Wang%2C+Shiwan+Zhao%2C+Jiabei+He%2C+Haoqin+Sun%2C+Hui+Wang%2C+Cheng+Liu%2C+Aobo+Kong%2C+Yujie+Guo%2C+Xi+Yang%2C+et+al%2E+2025a%2E+Childmandarin%3A+A+comprehensive+mandarin+speech+dataset+for+young+childr)
91. Siyi Zhou, Yiquan Zhou, Yi He, Xun Zhou, Jinchao Wang, Wei Deng, and Jingchen Shu. 2025b. 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+2025b%2E+Indextts2%3A+A+breakthrough+in+emotionally+expressive+and+duration%2Dcontrolled+auto%2Dregressive+zero%2Dshot+text%2Dto%2D)
92. Han Zhu, Wei Kang, Liyong Guo, Zengwei Yao, Fangjun Kuang, Weiji Zhuang, Zhaoqing Li, Zhifeng Han, Dong Zhang, Xin Zhang, et al. 2025a. [Zipvoice-dialog: Non-autoregressive spoken dialogue generation with flow matching](https://md.research.elamur.ai/free/en/papers/zhu-2026-zipvoice-dialog-non-autoregressive-spoken/). arXiv preprint arXiv:2507.09318.
93. Han Zhu, Wei Kang, Zengwei Yao, Liyong Guo, Fangjun Kuang, Zhaoqing Li, Weiji Zhuang, Long Lin, and Daniel Povey. 2025b. Zipvoice: Fast and high-quality zero-shot text-to-speech with flow matching. arXiv preprint arXiv:2506.13053. — [arXiv:2506.13053](https://arxiv.org/abs/2506.13053) [find](https://scholar.google.com/scholar?q=Han+Zhu%2C+Wei+Kang%2C+Zengwei+Yao%2C+Liyong+Guo%2C+Fangjun+Kuang%2C+Zhaoqing+Li%2C+Weiji+Zhuang%2C+Long+Lin%2C+and+Daniel+Povey%2E+2025b%2E+Zipvoice%3A+Fast+and+high%2Dquality+zero%2Dshot+text%2Dto%2Dspeech+with+flow+matching%2E+ar)

*Updated 2 November 2026*