{"url":"/dataset/flickr-audio-caption-corpus","name":"Flickr Audio Caption Corpus","full_name":"Flickr Audio Caption Corpus","description_markdown":"The Flickr 8k Audio Caption Corpus contains 40,000 spoken captions of 8,000 natural images. It was collected in 2015 to investigate multimodal learning schemes for unsupervised speech pattern discovery. For a description of the corpus, see:\r\n\r\nD. Harwath and J. Glass, \"Deep Multimodal Semantic Embeddings for Speech and Images,\" 2015 IEEE Automatic Speech Recognition and Understanding Workshop, pp. 237-244, Scottsdale, Arizona, USA, December 2015","description_withheld":null,"homepage":"https://groups.csail.mit.edu/sls/downloads/flickraudio/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[],"variants":["Flickr Audio Caption Corpus"],"data_loaders":[],"num_papers_in_archive":2,"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."}