@inproceedings{liu-liu-2026-synthetic,
    title = "Synthetic Doctor-Patient Dialogue Generation for Robust Medical {ASR}: A Scalable Pipeline for Vocabulary Expansion and Privacy Preservation",
    author = "Liu, Kefei  and
      Liu, Meizhu",
    editor = {Matusevych, Yevgen  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en  and
      Aletras, Nikolaos},
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-industry.40/",
    pages = "525--534",
    ISBN = "979-8-89176-384-5",
    abstract = "Automatic Speech Recognition (ASR) is increasingly integral to healthcare services, where medical conversations present unique transcription challenges due to specialized terminology and frequent introduction of new terms. Existing ASR models, including widely used systems like Whisper, struggle with high word error rates (WER) on clinical vocabulary, especially medication names, primarily due to the scarcity of annotated audio-transcript data in the medical domain. This paper proposes and evaluates a novel synthetic data generation pipeline that produces comprehensive doctor-patient dialogues in both text and audio forms, specifically targeting a curated set of over 124,000 medical terms. The pipeline generated over 1 billion audios with ground truth transcriptions. Fine-tuning ASR models with this synthetic corpus significantly reduced overall WER and improved transcription accuracy on medical terms, marking a significant advance in healthcare ASR accuracy. Data generation code, dataset, and training and evaluation scripts are released."
}