@inproceedings{roll-etal-2025-context,
    title = "In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties",
    author = "Roll, Nathan  and
      Graham, Calbert  and
      Tatsumi, Yuka  and
      Nguyen, Kim Tien  and
      Sumner, Meghan  and
      Jurafsky, Dan",
    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/ingest-emnlp/2025.emnlp-main.219/",
    pages = "4412--4426",
    ISBN = "979-8-89176-332-6",
    abstract = "Human listeners readily adjust to unfamiliar speakers and language varieties through exposure, but do these adaptation benefits extend to state-of-the-art spoken language models (SLMs)? We introduce a scalable framework that allows for in-context learning (ICL) in Phi-4 Multimodal (Phi-4-MM) using interleaved task prompts and audio-text pairs, and find that as few as 12 example utterances ({\textasciitilde}50 seconds) at inference time reduce word error rates by a relative 19.7{\%} (1.2 pp.) on average across diverse English corpora. These improvements are most pronounced in low-resource varieties, when the context and target speaker match, and when more examples are provided{---}though scaling our procedure yields diminishing marginal returns to context length. Overall, we find that our novel ICL adaptation scheme (1) reveals a similar performance profile to human listeners, and (2) demonstrates consistent improvements to automatic speech recognition (ASR) robustness across diverse speakers and language backgrounds. While adaptation succeeds broadly, significant gaps remain for certain varieties, revealing where current models still fall short of human flexibility. We release our prompts and code on GitHub."
}