@inproceedings{li-etal-2023-towards-noise,
    title = "Towards Noise-Tolerant Speech-Referring Video Object Segmentation: Bridging Speech and Text",
    author = "Li, Xiang  and
      Wang, Jinglu  and
      Xu, Xiaohao  and
      Yang, Muqiao  and
      Yang, Fan  and
      Zhao, Yizhou  and
      Singh, Rita  and
      Raj, Bhiksha",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.emnlp-main.140/",
    doi = "10.18653/v1/2023.emnlp-main.140",
    pages = "2283--2296"
}