{"url":"/dataset/emomusic","name":"Emomusic","full_name":"Emotion in Music Database","description_markdown":"1000 songs has been selected from Free Music Archive (FMA). The excerpts which were annotated are available in the same package song ids 1 to 1000. Some redundancies were identified, which reduced the dataset down to 744 songs. The dataset is split between the development set (619 songs) and the evaluation set (125 songs). The extracted 45 seconds excerpts are all re-encoded to have the same sampling frequency, i.e, 44100Hz. \r\n\r\nSource: [https://cvml.unige.ch/databases/emoMusic/](https://cvml.unige.ch/databases/emoMusic/)","description_withheld":null,"homepage":"https://cvml.unige.ch/databases/emoMusic/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Custom","url":"https://cvml.unige.ch/databases/emoMusic/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Music","url":"/datasets/modality/music"}],"tasks":[{"name":"Emotion Recognition","url":"/task/emotion-recognition","datasets_with_task":"/datasets/task/emotion-recognition"}],"languages":[],"variants":["Emomusic"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/emotion-recognition-on-emomusic","task":"Emotion Recognition","dataset_variant":"Emomusic","rows":5,"metrics":["EmoA","EmoV"],"first_row_in_archive_order":{"model":"M2D-CLAP","paper":"/paper/m2d2-exploring-general-purpose-audio-language","metrics":{"EmoA":"77.4","EmoV":"61.9"},"code_links":[{"title":"nttcslab/m2d","url":"https://github.com/nttcslab/m2d"},{"title":"nttcslab/eval-audio-repr","url":"https://github.com/nttcslab/eval-audio-repr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/codified-audio-language-modeling-learns","title":"Codified audio language modeling learns useful representations for music information retrieval","date":"2021-07-12","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":3,"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."}