{"url":"/dataset/sms-wsj","name":"SMS-WSJ","full_name":"Spatialized Multi-Speaker Wall Street Journal","description_markdown":"Spatialized Multi-Speaker Wall Street Journal (SMS-WSJ) consists of artificially mixed speech taken from the WSJ database, but unlike earlier databases this one considers all WSJ0+1 utterances and takes care of strictly separating the speaker sets present in the training, validation and test sets. \r\n\r\nSource: [SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition](/paper/sms-wsj-database-performance-measures-and)","description_withheld":null,"homepage":"https://github.com/fgnt/sms_wsj","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/sms-wsj-database-performance-measures-and","title":"SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition","first_author":"Lukas Drude","url":null},"license":null,"modalities":[],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Audio Source Separation","url":"/task/audio-source-separation","datasets_with_task":"/datasets/task/audio-source-separation"}],"languages":[],"variants":["SMS-WSJ"],"data_loaders":[{"repo":"https://github.com/fgnt/sms_wsj","url":"https://github.com/fgnt/sms_wsj","frameworks":[]}],"num_papers_in_archive":14,"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."}