{"url":"/dataset/alimeeting","name":"AliMeeting","full_name":"Multi-Channel Multi-Party Meeting Transcription Challenge","description_markdown":"AliMeeting corpus consists of 120 hours of recorded Mandarin meeting data, including far-field data collected by 8-channel microphone array as well as near-field data collected by headset microphone. Each meeting session is composed of 2-4 speakers with different speaker overlap ratio, recorded in rooms with different size.","description_withheld":null,"homepage":"https://www.alibabacloud.com/zh/m2met-alimeeting","introduced_date":"2021-10-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/m2met-the-icassp-2022-multi-channel-multi","title":"M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge","first_author":null,"url":null},"license":{"name":"MIT License","url":"https://opensource.org/license/mit/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Speaker Diarization","url":"/task/speaker-diarization","datasets_with_task":"/datasets/task/speaker-diarization"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["AliMeeting"],"data_loaders":[],"num_papers_in_archive":46,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speaker-diarization-on-alimeeting","task":"Speaker Diarization","dataset_variant":"AliMeeting","rows":1,"metrics":["DER(%)"],"first_row_in_archive_order":{"model":"SOND","paper":"/paper/speaker-embedding-aware-neural-diarization-a","metrics":{"DER(%)":"4.46"},"code_links":[{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/speaker-embedding-aware-neural-diarization-a","title":"Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios","date":"2022-03-18","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."}