@inproceedings{retkowski-etal-2025-summarizing,
    title = "Summarizing Speech: A Comprehensive Survey",
    author = {Retkowski, Fabian  and
      Z{\"u}fle, Maike  and
      Sudmann, Andreas  and
      Pfau, Dinah  and
      Watanabe, Shinji  and
      Niehues, Jan  and
      Waibel, Alexander},
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.emnlp-main.1388/",
    doi = "10.18653/v1/2025.emnlp-main.1388",
    pages = "27263--27294",
    ISBN = "979-8-89176-332-6",
    abstract = "Speech summarization has become an essential tool for efficiently managing and accessing the growing volume of spoken and audiovisual content. However, despite its increasing importance, speech summarization remains loosely defined. The field intersects with several research areas, including speech recognition, text summarization, and specific applications like meeting summarization. This survey not only examines existing datasets and evaluation protocols, which are crucial for assessing the quality of summarization approaches, but also synthesizes recent developments in the field, highlighting the shift from traditional systems to advanced models like fine-tuned cascaded architectures and end-to-end solutions. In doing so, we surface the ongoing challenges, such as the need for realistic evaluation benchmarks, multilingual datasets, and long-context handling."
}