SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation

Mu et al. "SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation." International Joint Conference on Artificial Intelligence, 2025. doi:10.24963/IJCAI.2025/912

[Mu et al. "SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation." International Joint Conference on Artificial Intelligence, 2025.](https://mlanthology.org/ijcai/2025/mu2025ijcai-sepalm/) doi:10.24963/IJCAI.2025/912

@inproceedings{mu2025ijcai-sepalm,
  title     = {{SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation}},
  author    = {Mu, Zhaoxi and Yang, Xinyu and Wang, Gang},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {8204-8212},
  doi       = {10.24963/IJCAI.2025/912},
  url       = {https://mlanthology.org/ijcai/2025/mu2025ijcai-sepalm/}
}