{"url":"/dataset/common-phone","name":"Common Phone","full_name":null,"description_markdown":"**Common Phone** is a gender-balanced, multilingual corpus recorded from more than 76.000 contributors via Mozilla's Common Voice project. It comprises around 116 hours of speech enriched with automatically generated phonetic segmentation.","description_withheld":null,"homepage":"https://arxiv.org/pdf/2201.05912v1.pdf","introduced_date":"2022-01-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/common-phone-a-multilingual-dataset-for","title":"Common Phone: A Multilingual Dataset for Robust Acoustic Modelling","first_author":"Philipp Klumpp","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[],"variants":["Common Phone"],"data_loaders":[],"num_papers_in_archive":6,"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."}