{"url":"/dataset/voxclamantis","name":"VoxClamantis","full_name":null,"description_markdown":"A large-scale corpus for phonetic typology, with aligned segments and estimated phoneme-level labels in 690 readings spanning 635 languages, along with acoustic-phonetic measures of vowels and sibilants. \r\n\r\nSource: [A Corpus for Large-Scale Phonetic Typology](/paper/a-corpus-for-large-scale-phonetic-typology)","description_withheld":null,"homepage":"https://voxclamantisproject.github.io/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-corpus-for-large-scale-phonetic-typology","title":"A Corpus for Large-Scale Phonetic Typology","first_author":"Elizabeth Salesky","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[],"variants":["VoxClamantis"],"data_loaders":[],"num_papers_in_archive":5,"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."}