{"url":"/dataset/ears-wham","name":"EARS-WHAM","full_name":null,"description_markdown":"The EARS-WHAM dataset mixes speech from the EARS dataset with real noise recordings from the WHAM! dataset. Speech and noise files are mixed at signal-to-noise ratios (SNRs) randomly sampled in a range of [−2.5, 17.5] dB, where the SNR is computed using loudness K- weighted relative to full scale (LKFS) standardized in ITU-R BS.1770 to obtain a more perceptually meaningful scaling and also to remove silent regions from the SNR computation.","description_withheld":null,"homepage":"https://sp-uhh.github.io/ears_dataset/","introduced_date":"2024-06-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/ears-an-anechoic-fullband-speech-dataset","title":"EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation","first_author":"Julius Richter","url":null},"license":{"name":"CC-NC 4.0 International license","url":"https://github.com/facebookresearch/ears_dataset/blob/main/LICENSE"},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Enhancement","url":"/task/speech-enhancement","datasets_with_task":"/datasets/task/speech-enhancement"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["EARS-WHAM"],"data_loaders":[],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-enhancement-on-ears-wham","task":"Speech Enhancement","dataset_variant":"EARS-WHAM","rows":6,"metrics":["PESQ-WB","SI-SDR","ESTOI","SIGMOS","DNSMOS","POLQA"],"first_row_in_archive_order":{"model":"Schrödinger Bridge (PESQ loss)","paper":"/paper/investigating-training-objectives-for","metrics":{"DNSMOS":"3.72","ESTOI":"0.73","PESQ-WB":"3.09","POLQA":"3.71","SI-SDR":"16.29","SIGMOS":"3.18"},"code_links":[{"title":"sp-uhh/sgmse","url":"https://github.com/sp-uhh/sgmse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/investigating-training-objectives-for","title":"Investigating Training Objectives for Generative Speech Enhancement","date":"2024-09-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/schrodinger-bridge-for-generative-speech","title":"Schrödinger Bridge for Generative Speech Enhancement","date":"2024-07-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hybrid-transformers-for-music-source","title":"Hybrid Transformers for Music Source Separation","date":"2022-11-15","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/speech-enhancement-and-dereverberation-with","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","date":"2022-08-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/conditional-diffusion-probabilistic-model-for","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","date":"2022-02-10","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/tasnet-surpassing-ideal-time-frequency","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","date":"2018-09-20","rows_on_this_dataset":1,"code_links":17,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":36,"samples_ran":7,"samples_unverified":29,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":46,"samples_ran":7,"samples_unverified":39,"pointer_only_for_licence":26,"papers_with_no_sample_that_ran":1,"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."}