Jiaqi Li's Homepage

@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.},
}

@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.},
}

@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.},
}

@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.},
}

@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.},
}

@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},
}

@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.},
}

@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.},
}

@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},
}

@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},
}