{"url":"/dataset/gtzan-music-speech","name":"gtzan_music_speech","full_name":"gtzan_music_speech","description_markdown":"**gtzan_music_speech** is a dataset for music/speech discrimination. It consists of 120 tracks of 30 second length. Each class (music/speech) has 60 samples. The tracks are all 22050Hz Mono 16-bit audio files in .wav format.","description_withheld":null,"homepage":"http://marsyas.info/index.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[],"languages":[],"variants":["gtzan_music_speech"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/gtzan-music-speech-dataset","frameworks":[]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/gtzan_music_speech","frameworks":["tf","jax"]}],"num_papers_in_archive":1,"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."}