{"url":"/dataset/detoxy","name":"DeToxy","full_name":"DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances","description_markdown":"**DeToxy** is a publicly available toxicity annotated dataset for the English language. DeToxy is sourced from various openly available speech databases and consists of over 2 million utterances. The dataset would act as a benchmark for the relatively new and un-explored Spoken Language Processing task of detecting toxicity from spoken utterances and boost further research in this space.","description_withheld":null,"homepage":"https://github.com/sreyan88/toxicity-detection-in-spoken-utterances","introduced_date":"2021-10-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/speech-toxicity-analysis-a-new-spoken","title":"DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances","first_author":"Sreyan Ghosh","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Hate Speech Detection","url":"/task/hate-speech-detection","datasets_with_task":"/datasets/task/hate-speech-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DeToxy"],"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."}