{"url":"/dataset/dsd100","name":"DSD100","full_name":null,"description_markdown":"The dsd100 is a dataset of 100 full lengths of music tracks of different styles along with their isolated drums, bass, vocals, and other stems.\r\n\r\ndsd100 contains two folders, a folder with a training set: \"train\", composed of 50 songs, and a folder with a test set: \"test\", composed of 50 songs. Supervised approaches should be trained on the training set and tested on both sets.\r\n\r\nFor each file, the mixture corresponds to the sum of all the signals. All signals are stereophonic and encoded at 44.1kHz.","description_withheld":null,"homepage":"https://sigsep.github.io/datasets/dsd100.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Audio Super-Resolution","url":"/task/audio-super-resolution","datasets_with_task":"/datasets/task/audio-super-resolution"}],"languages":[],"variants":["DSD100"],"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/audio-super-resolution-on-dsd100","task":"Audio Super-Resolution","dataset_variant":"DSD100","rows":1,"metrics":["SNR"],"first_row_in_archive_order":{"model":"U-Net and ResNet","paper":"/paper/on-filter-generalization-for-music-bandwidth","metrics":{"SNR":"35.26"},"code_links":[{"title":"serkansulun/deep-music-enhancer","url":"https://github.com/serkansulun/deep-music-enhancer"},{"title":"serkansulun/deep-music-enhancement","url":"https://github.com/serkansulun/deep-music-enhancement"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/on-filter-generalization-for-music-bandwidth","title":"On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks","date":"2020-11-14","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"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."}