publications

2026

1. EMNLP 2026

   FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates

   Jiaqi Li, Chaoren Wang, Xiaohai Tian, Mingjie Chen, Xinyu Liang, Xu Li, Yufan Lin, Junwen Qiu, Jun Zhang, Lu Lu, Haizhou Li, and Zhizheng Wu

   In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026

   arXiv Bib Code Website

   @inproceedings{li2026flexislm,
     title = {FlexiSLM: A Spoken Language Model with Dynamic and Controllable Frame Rates},
     author = {Li, Jiaqi and Wang, Chaoren and Tian, Xiaohai and Chen, Mingjie and Liang, Xinyu and Li, Xu and Lin, Yufan and Qiu, Junwen and Zhang, Jun and Lu, Lu and Li, Haizhou and Wu, Zhizheng},
     booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
     year = {2026},
     tldr = {We introduce the first spoken language model with dynamic and controllable frame rates for speech input and output.},
   }

   TL;DR: We introduce the first spoken language model with dynamic and controllable frame rates for speech input and output.
2. EMNLP 2026

   SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision

   Rongshen He, Xinyu Liang, Dekun Chen, Jiaqi Li, Mingjie Chen, and Zhizheng Wu

   In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026

   arXiv Bib Website

   @inproceedings{he2026simuls2stomni,
     title = {SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision},
     author = {He, Rongshen and Liang, Xinyu and Chen, Dekun and Li, Jiaqi and Chen, Mingjie and Wu, Zhizheng},
     booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
     year = {2026},
     tldr = {We enable data-efficient long-form streaming speech-to-speech translation with joint text-code trajectory supervision.},
   }

   TL;DR: We enable data-efficient long-form streaming speech-to-speech translation with joint text-code trajectory supervision.
3. ICLR 2026

   FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates

   Jiaqi Li, Yao Qian, Yuxuan Hu, Leying Zhang, Xiaofei Wang, Heng Lu, Manthan Thakker, Jinyu Li, Sheng Zhao, and Zhizheng Wu

   In International Conference on Learning Representations (ICLR), 2026

   arXiv Bib Code Website

   @inproceedings{li2026flexicodec,
     title = {FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates},
     author = {Li, Jiaqi and Qian, Yao and Hu, Yuxuan and Zhang, Leying and Wang, Xiaofei and Lu, Heng and Thakker, Manthan and Li, Jinyu and Zhao, Sheng and Wu, Zhizheng},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2026},
     tldr = {We develop a dynamic neural audio codec with controllable low frame rates for efficient speech generation.},
   }

   TL;DR: We develop a dynamic neural audio codec with controllable low frame rates for efficient speech generation.

2025

1. Interspeech 2025

   DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation

   Jiaqi Li, Xiaolong Lin, Zhekai Li, Shixi Huang, Yuancheng Wang, Chaoren Wang, Zhenpeng Zhan, and Zhizheng Wu

   In Proceedings of Interspeech 2025, 2025

   arXiv Bib Code Website

   @inproceedings{li2025dualcodec,
     title = {DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation},
     author = {Li, Jiaqi and Lin, Xiaolong and Li, Zhekai and Huang, Shixi and Wang, Yuancheng and Wang, Chaoren and Zhan, Zhenpeng and Wu, Zhizheng},
     booktitle = {Proceedings of Interspeech 2025},
     year = {2025},
     tldr = {We propose a low-frame-rate neural audio codec that strengthens semantic information for speech generation.},
   }

   TL;DR: We propose a low-frame-rate neural audio codec that strengthens semantic information for speech generation.
2. Tech Report

   Overview of the Amphion Toolkit (v0. 2)

   Jiaqi Li, Xueyao Zhang, Yuancheng Wang, Haorui He, Chaoren Wang, Li Wang, Huan Liao, Junyi Ao, Zeyu Xie, Yiqiao Huang, and  others

   arXiv preprint arXiv:2501.15442, 2025

   arXiv Bib Code Huggingface

   @article{li2025overview,
     title = {Overview of the Amphion Toolkit (v0. 2)},
     author = {Li, Jiaqi and Zhang, Xueyao and Wang, Yuancheng and He, Haorui and Wang, Chaoren and Wang, Li and Liao, Huan and Ao, Junyi and Xie, Zeyu and Huang, Yiqiao and others},
     journal = {arXiv preprint arXiv:2501.15442},
     year = {2025},
     huggingface = {https://huggingface.co/amphion},
     tldr = {This is the technical report for the second version of the Amphion toolkit.},
   }

   TL;DR: This is the technical report for the second version of the Amphion toolkit.

2024

1. SLT 2024

   Investigating neural audio codecs for speech language model-based speech generation

   Jiaqi Li, Dongmei Wang, Xiaofei Wang, Yao Qian, Long Zhou, Shujie Liu, Midia Yousefi, Canrun Li, Chung-Hsien Tsai, Zhen Xiao, and  others

   In 2024 IEEE Spoken Language Technology Workshop (SLT), 2024

   arXiv Bib

   @inproceedings{li2024investigating,
     title = {Investigating neural audio codecs for speech language model-based speech generation},
     author = {Li, Jiaqi and Wang, Dongmei and Wang, Xiaofei and Qian, Yao and Zhou, Long and Liu, Shujie and Yousefi, Midia and Li, Canrun and Tsai, Chung-Hsien and Xiao, Zhen and others},
     booktitle = {2024 IEEE Spoken Language Technology Workshop (SLT)},
     pages = {554--561},
     year = {2024},
     organization = {IEEE},
   }
2. SLT 2024

   Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation

   Haorui He, Zengqiang Shang, Chaoren Wang, Xuyuan Li, Yicheng Gu, Hua Hua, Liwei Liu, Chen Yang, Jiaqi Li, Peiyang Shi, Yuancheng Wang, Kai Chen, Pengyuan Zhang, and Zhizheng Wu

   In 2024 IEEE Spoken Language Technology Workshop (SLT), 2024

   arXiv Bib Huggingface

   @inproceedings{he2024emilia,
     title = {Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation},
     author = {He, Haorui and Shang, Zengqiang and Wang, Chaoren and Li, Xuyuan and Gu, Yicheng and Hua, Hua and Liu, Liwei and Yang, Chen and Li, Jiaqi and Shi, Peiyang and Wang, Yuancheng and Chen, Kai and Zhang, Pengyuan and Wu, Zhizheng},
     booktitle = {2024 IEEE Spoken Language Technology Workshop (SLT)},
     year = {2024},
     huggingface = {https://huggingface.co/datasets/amphion/Emilia},
     tldr = {We collect a 100k hours in-the-wild speech dataset for speech generation.},
   }

   TL;DR: We collect a 100k hours in-the-wild speech dataset for speech generation.
3. SLT 2024

   Amphion: an Open-Source Audio, Music, and Speech Generation Toolkit

   Xueyao Zhang^*, Liumeng Xue^*, Yicheng Gu^*, Yuancheng Wang^*, Jiaqi Li, Haorui He, Chaoren Wang, Songting Liu, Xi Chen, Junan Zhang, Tze Ying Tang, Lexiao Zou, Mingxuan Wang, Jun Han, Kai Chen, Haizhou Li, and Zhizheng Wu

   In 2024 IEEE Spoken Language Technology Workshop (SLT), 2024

   arXiv Bib Code Huggingface

   @inproceedings{zhang2024amphion,
     title = {Amphion: an Open-Source Audio, Music, and Speech Generation Toolkit
     },
     author = {Zhang, Xueyao and Xue, Liumeng and Gu, Yicheng and Wang, Yuancheng and Li, Jiaqi and He, Haorui and Wang, Chaoren and Liu, Songting and Chen, Xi and Zhang, Junan and Tang, Tze Ying and Zou, Lexiao and Wang, Mingxuan and Han, Jun and Chen, Kai and Li, Haizhou and Wu, Zhizheng},
     booktitle = {2024 IEEE Spoken Language Technology Workshop (SLT)},
     year = {2024},
     huggingface = {https://huggingface.co/amphion},
     tldr = {We develop a unified toolkit for audio, music, and speech generation.},
   }

   TL;DR: We develop a unified toolkit for audio, music, and speech generation.
4. ICASSP 2024

   An initial investigation of neural replay simulator for over-the-air adversarial perturbations to automatic speaker verification

   Jiaqi Li, Li Wang, Liumeng Xue, Lei Wang, and Zhizheng Wu

   In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

   arXiv Bib

   @inproceedings{li2024initial,
     title = {An initial investigation of neural replay simulator for over-the-air adversarial perturbations to automatic speaker verification},
     author = {Li, Jiaqi and Wang, Li and Xue, Liumeng and Wang, Lei and Wu, Zhizheng},
     booktitle = {ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {4635--4639},
     year = {2024},
     organization = {IEEE},
   }
5. ICASSP 2024

   Advsv: An over-the-air adversarial attack dataset for speaker verification

   Li Wang, Jiaqi Li, Yuhao Luo, Jiahao Zheng, Lei Wang, Hao Li, Ke Xu, Chengfang Fang, Jie Shi, and Zhizheng Wu

   In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

   arXiv Bib

   @inproceedings{wang2024advsv,
     title = {Advsv: An over-the-air adversarial attack dataset for speaker verification},
     author = {Wang, Li and Li, Jiaqi and Luo, Yuhao and Zheng, Jiahao and Wang, Lei and Li, Hao and Xu, Ke and Fang, Chengfang and Shi, Jie and Wu, Zhizheng},
     booktitle = {ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {4555--4559},
     year = {2024},
     organization = {IEEE},
   }
6. Debatts: Zero-shot debating text-to-speech synthesis

   Yiqiao Huang, Yuancheng Wang, Jiaqi Li, Haotian Guo, Haorui He, Shunsi Zhang, and Zhizheng Wu

   arXiv preprint arXiv:2411.06540, 2024

2023

1. ROME: Testing image captioning systems via recursive object melting

   Boxi Yu, Zhiqing Zhong, Jiaqi Li, Yixing Yang, Shilin He, and Pinjia He

   In Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis, 2023