{"url":"/dataset/united-syn-med","name":"United-Syn-Med","full_name":null,"description_markdown":"The United-Syn-Med dataset is a specialized medical speech dataset designed to evaluate and improve Automatic Speech Recognition (ASR) systems within the healthcare domain. It comprises English medical speech recordings, with a particular focus on medical terminology and clinical conversations. The dataset is well-suited for various ASR tasks, including speech recognition, transcription, and classification, facilitating the development of models tailored for medical contexts.\r\n\r\nThis dataset supports a broad range of applications, including medical documentation automation, transcription of doctor-patient conversations, and medical knowledge extraction from audio data.","description_withheld":null,"homepage":"https://huggingface.co/datasets/united-we-care/United-Syn-Med","introduced_date":"2024-10-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/high-precision-medical-speech-recognition","title":"High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR","first_author":"Sourav Banerjee","url":null},"license":{"name":"Creative Commons Attribution Share Alike 4.0","url":"https://choosealicense.com/licenses/cc-by-sa-4.0/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Speech Synthesis","url":"/task/speech-synthesis","datasets_with_task":"/datasets/task/speech-synthesis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["United-Syn-Med"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}