@inproceedings{bharadwaj-etal-2026-prism,
    title = "{PR}i{SM}: Benchmarking Phone Realization in Speech Models",
    author = "Bharadwaj, Shikhar  and
      Li, Chin-Jou  and
      Kim, Yoonjae  and
      Choi, Kwanghee  and
      Yeo, Eunjung  and
      Shim, Ryan Soh-Eun  and
      Zhou, Hanyu  and
      Boldt, Brendon  and
      Rosero, Karen  and
      Chang, Kalvin  and
      Agrawal, Darsh  and
      Xu, Keer  and
      Yang, Chao-Han Huck  and
      Zhu, Jian  and
      Watanabe, Shinji  and
      Mortensen, David R.",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.825/",
    pages = "18093--18112",
    ISBN = "979-8-89176-390-6",
    abstract = "Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis. Despite prolonged efforts in developing PR systems, current evaluations only measure surface-level transcription accuracy. We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception through intrinsic and extrinsic evaluation of PR systems. PRiSM standardizes transcription-based evaluation and assesses downstream utility in clinical, educational, and multilingual settings with transcription and representation probes. We find that diverse language exposure during training is key to PR performance, encoder-CTC models are the most stable, and specialized PR systems still outperform LALMs. PRiSM releases code, recipes, and datasets to move the field toward multilingual speech models with robust phonetic ability."
}