@inproceedings{cui-etal-2025-recent,
    title = "Recent Advances in Speech Language Models: A Survey",
    author = "Cui, Wenqian  and
      Yu, Dianzhi  and
      Jiao, Xiaoqi  and
      Meng, Ziqiao  and
      Zhang, Guangyan  and
      Wang, Qichao  and
      Guo, Steven Y.  and
      King, Irwin",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.682/",
    pages = "13943--13970",
    ISBN = "979-8-89176-251-0",
    abstract = "Text-based Large Language Models (LLMs) have recently gained significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, highlighting the need for voice-based models. In this context, Speech Language Models (SpeechLMs){---}foundation models designed to understand and generate speech{---}emerge as a promising solution for end-to-end speech interaction. This survey offers a comprehensive overview of recent approaches to building SpeechLMs, outlining their core architectural components, training methodologies, evaluation strategies, and the challenges and potential directions for future research in this rapidly advancing field. The GitHub repository is available at https://github.com/dreamtheater123/Awesome-SpeechLM-Survey"
}