{"url":"/dataset/ccmixter","name":"CCMixter","full_name":null,"description_markdown":"**CCMixter** is a singing voice separation dataset consisting of 50 full-length stereo tracks from [ccMixter](www.ccmixter.org) featuring many different musical genres. For each song there are three WAV files available: the background music, the voice signal, and their sum.\n\nSource: [Kernel Additive Models for Source Separation](https://doi.org/10.1109/TSP.2014.2332434)\nAudio Source: [https://members.loria.fr/ALiutkus/kam/](https://members.loria.fr/ALiutkus/kam/)","description_withheld":null,"homepage":"https://members.loria.fr/ALiutkus/kam/","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Kernel Additive Models for Source Separation","first_author":null,"url":"https://doi.org/10.1109/TSP.2014.2332434"},"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[],"languages":[],"variants":["CCMixter"],"data_loaders":[],"num_papers_in_archive":6,"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."}