{"url":"/dataset/synthsod","name":"SynthSOD","full_name":null,"description_markdown":"The SynthSOD dataset contains more than 47 hours of multitrack music obtained by synthesizing orchestra and ensemble pieces from the Symbolic Orchestral Database (SOD) using Spitfire BBC Symphony Orchestra Professional Library. To synthesize the MIDI files from the SOD, we needed to fix the original files into the General MIDI standard, select a subsect of files that fitted into our requirements (e.g.,  containing only instruments that we could synthesize), and develop a new system to generate musically-motivated random annotations about tempo, dynamic, and articulation.","description_withheld":null,"homepage":"https://zenodo.org/records/13759492","introduced_date":"2024-09-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/synthsod-developing-an-heterogeneous-dataset","title":"SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source Separation","first_author":"Jaime Garcia-Martinez","url":null},"license":{"name":"Creative Commons Attribution Share Alike 4.0 International","url":null},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Music","url":"/datasets/modality/music"}],"tasks":[{"name":"Music Source Separation","url":"/task/music-source-separation","datasets_with_task":"/datasets/task/music-source-separation"}],"languages":[],"variants":["SynthSOD"],"data_loaders":[],"num_papers_in_archive":2,"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."}