{"url":"/dataset/speech-coco","name":"SPEECH-COCO","full_name":null,"description_markdown":"SPEECH-COCO contains speech captions that are generated using text-to-speech (TTS) synthesis resulting in 616,767 spoken captions (more than 600h) paired with images. \r\n\r\nSource: [SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set](/paper/speech-coco-600k-visually-grounded-spoken)","description_withheld":null,"homepage":"https://zenodo.org/record/4282267","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/speech-coco-600k-visually-grounded-spoken","title":"SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set","first_author":"William Havard","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Intent Detection","url":"/task/intent-detection","datasets_with_task":"/datasets/task/intent-detection"},{"name":"Fairness","url":"/task/fairness","datasets_with_task":"/datasets/task/fairness"}],"languages":[],"variants":["SPEECH-COCO"],"data_loaders":[],"num_papers_in_archive":9,"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."}