{"url":"/dataset/macs","name":"MACS","full_name":"Multi-Annotator Captioned Soundscapes","description_markdown":"This is a dataset containing audio captions and corresponding audio tags for a number of 3930 audio files of the TAU Urban Acoustic Scenes 2019 development dataset (airport, public square, and park). The files were annotated using a web-based tool. Each file is annotated by multiple annotators that provided tags and a one-sentence description of the audio content.","description_withheld":null,"homepage":"https://zenodo.org/records/5114771","introduced_date":"2021-11-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/diversity-and-bias-in-audio-captioning","title":"Diversity and bias in audio captioning datasets","first_author":"Irene Martin-Morato","url":null},"license":{"name":"Other (Non commercial)","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Audio captioning","url":"/task/audio-captioning","datasets_with_task":"/datasets/task/audio-captioning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MACS"],"data_loaders":[{"repo":"https://github.com/labbeti/aac-datasets","url":"https://aac-datasets.readthedocs.io/en/stable/","frameworks":["pytorch"]}],"num_papers_in_archive":10,"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."}