{"url":"/dataset/e-gmd","name":"E-GMD","full_name":"Expanded Groove MIDI Dataset","description_markdown":"Expanded Groove MIDI dataset (E-GMD) is an automatic drum transcription (ADT) dataset that contains 444 hours of audio from 43 drum kits, making it an order of magnitude larger than similar datasets, and the first with human-performed velocity annotations.\r\n\r\nSource: [Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset](https://arxiv.org/pdf/2004.00188)","description_withheld":null,"homepage":"https://storage.googleapis.com/magentadata/papers/e-gmd/index.html","introduced_date":"2020-04-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/improving-perceptual-quality-of-drum","title":"Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset","first_author":"Lee Callender","url":null},"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Midi","url":"/datasets/modality/midi"}],"tasks":[{"name":"Drum Transcription","url":"/task/drum-transcription","datasets_with_task":"/datasets/task/drum-transcription"}],"languages":[],"variants":["E-GMD"],"data_loaders":[],"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."}