{"url":"/dataset/cn-celeb","name":"CN-CELEB","full_name":null,"description_markdown":"CN-Celeb is a large-scale speaker recognition dataset collected `in the wild'. This dataset contains more than 130,000 utterances from 1,000 Chinese celebrities, and covers 11 different genres in real world.\r\n\r\nSource: [CN-CELEB: a challenging Chinese speaker recognition dataset](/paper/cn-celeb-a-challenging-chinese-speaker)","description_withheld":null,"homepage":"http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/CN-Celeb","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/cn-celeb-a-challenging-chinese-speaker","title":"CN-CELEB: a challenging Chinese speaker recognition dataset","first_author":"Yue Fan","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speaker Verification","url":"/task/speaker-verification","datasets_with_task":"/datasets/task/speaker-verification"},{"name":"Dimensionality Reduction","url":"/task/dimensionality-reduction","datasets_with_task":"/datasets/task/dimensionality-reduction"},{"name":"Speaker Recognition","url":"/task/speaker-recognition","datasets_with_task":"/datasets/task/speaker-recognition"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CN-CELEB"],"data_loaders":[],"num_papers_in_archive":68,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speaker-verification-on-cn-celeb","task":"Speaker Verification","dataset_variant":"CN-CELEB","rows":2,"metrics":["EER"],"first_row_in_archive_order":{"model":"X-Vectors with Attention Backend","paper":"/paper/attention-back-end-for-automatic-speaker","metrics":{"EER":"10.12"},"code_links":[{"title":"nii-yamagishilab/Attention_Backend_for_ASV","url":"https://github.com/nii-yamagishilab/Attention_Backend_for_ASV"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/attention-back-end-for-automatic-speaker","title":"Attention Back-end for Automatic Speaker Verification with Multiple Enrollment Utterances","date":"2021-04-04","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}