{"url":"/dataset/wsj0-2mix-extr","name":"WSJ0-2mix-extr","full_name":null,"description_markdown":"WSJ0-2mix-extr is a speech extraction dataset","description_withheld":null,"homepage":"https://github.com/xuchenglin28/speaker_extraction_SpEx/tree/master/data/wsj0_2mix","introduced_date":"2020-04-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/spex-multi-scale-time-domain-speaker","title":"SpEx: Multi-Scale Time Domain Speaker Extraction Network","first_author":"Cheng-Lin Xu","url":null},"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Speech Extraction","url":"/task/speech-extraction","datasets_with_task":"/datasets/task/speech-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WSJ0-2mix-extr"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-extraction-on-wsj0-2mix-extr","task":"Speech Extraction","dataset_variant":"WSJ0-2mix-extr","rows":1,"metrics":["SI-SDR"],"first_row_in_archive_order":{"model":"SpEx+ (tied)","paper":null,"metrics":{"SI-SDR":"18.20"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"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."}