{"url":"/dataset/babel","name":"BABEL Project","full_name":"BABEL","description_markdown":"**BABEL** is a multilingual corpus of conversational telephone speech from IARPA, which includes Asian and African languages.","description_withheld":null,"homepage":"http://www.reading.ac.uk/AcaDepts/ll/speechlab/babel/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[],"variants":[],"data_loaders":[],"num_papers_in_archive":0,"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."}