{"url":"/dataset/hcu400","name":"HCU400","full_name":null,"description_markdown":"The dataset consists of the features associated with 402 5-second sound samples.\nThe 402 sounds range from easily identifiable everyday sounds to intentionally obscured artificial ones. The dataset aims to lower the barrier for the study of aural phenomenology as the largest available audio dataset to include an analysis of causal attribution. Each sample has been annotated with crowd-sourced descriptions, as well as familiarity, imageability, arousal, and valence ratings.\n\nSource: [https://github.com/mitmedialab/HCU400](https://github.com/mitmedialab/HCU400)","description_withheld":null,"homepage":"https://github.com/mitmedialab/HCU400","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/hcu400-an-annotated-dataset-for-exploring","title":"HCU400: An Annotated Dataset for Exploring Aural Phenomenology Through Causal Uncertainty","first_author":"Ishwarya Ananthabhotla","url":null},"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[],"variants":["HCU400"],"data_loaders":[{"repo":"https://github.com/mitmedialab/HCU400","url":"https://github.com/mitmedialab/HCU400","frameworks":[]}],"num_papers_in_archive":3,"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."}