{"url":"/dataset/dihard-ii","name":"DIHARD II","full_name":null,"description_markdown":"The DIHARD II development and evaluation sets draw from a diverse set of sources exhibiting wide variation in recording equipment, recording environment, ambient noise, number of speakers, and speaker demographics. The development set includes reference diarization and speech segmentation and may be used for any purpose including system development or training.","description_withheld":null,"homepage":"https://dihardchallenge.github.io/dihard2/","introduced_date":"2019-06-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-second-dihard-diarization-challenge","title":"The Second DIHARD Diarization Challenge: Dataset, task, and baselines","first_author":"Neville Ryant","url":null},"license":{"name":"Custom","url":"https://dihardchallenge.github.io/dihard2/#license"},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speaker Diarization","url":"/task/speaker-diarization","datasets_with_task":"/datasets/task/speaker-diarization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DIHARD II"],"data_loaders":[],"num_papers_in_archive":34,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speaker-diarization-on-dihard-ii","task":"Speaker Diarization","dataset_variant":"DIHARD II","rows":1,"metrics":["DER(%)","DER - no overlap"],"first_row_in_archive_order":{"model":"UIS-RNN-SML","paper":"/paper/supervised-online-diarization-with-sample","metrics":{"DER - no overlap":"19.4","DER(%)":"27.3"},"code_links":[{"title":"DonkeyShot21/uis-rnn-sml","url":"https://github.com/DonkeyShot21/uis-rnn-sml"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/supervised-online-diarization-with-sample","title":"Supervised online diarization with sample mean loss for multi-domain data","date":"2019-11-04","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}