{"url":"/dataset/real-m","name":"REAL-M","full_name":null,"description_markdown":"**Real-M** is a crowd-sourced speech-separation corpus of real-life mixtures. The mixtures are recorded in different acoustic environments using a wide variety of recording devices such as laptops and smartphones, thus reflecting more closely potential application scenarios.","description_withheld":null,"homepage":"https://sourceseparationresearch.com/static/REAL-M-v0.1.0.tar.gz","introduced_date":"2021-10-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/real-m-towards-speech-separation-on-real","title":"REAL-M: Towards Speech Separation on Real Mixtures","first_author":"Cem Subakan","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Separation","url":"/task/speech-separation","datasets_with_task":"/datasets/task/speech-separation"}],"languages":[],"variants":["REAL-M"],"data_loaders":[],"num_papers_in_archive":4,"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."}