{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":6,"of":6,"counts":{"papers_with_a_benchmark_row":6,"with_a_code_link":5,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":6,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/investigating-training-objectives-for","slug":"investigating-training-objectives-for","title":"Investigating Training Objectives for Generative Speech Enhancement","date":"2024-09-16","arxiv_id":"2409.10753","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/schrodinger-bridge-for-generative-speech","slug":"schrodinger-bridge-for-generative-speech","title":"Schrödinger Bridge for Generative Speech Enhancement","date":"2024-07-22","arxiv_id":"2407.16074","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hybrid-transformers-for-music-source","slug":"hybrid-transformers-for-music-source","title":"Hybrid Transformers for Music Source Separation","date":"2022-11-15","arxiv_id":"2211.08553","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":10,"official":{"repos":["facebookresearch/demucs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hybrid-transformers-for-music-source#ran","syntology_url":"https://syntology.ai/paper/2211.08553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08553"}}}},{"paper":"/paper/speech-enhancement-and-dereverberation-with","slug":"speech-enhancement-and-dereverberation-with","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","date":"2022-08-11","arxiv_id":"2208.05830","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/conditional-diffusion-probabilistic-model-for","slug":"conditional-diffusion-probabilistic-model-for","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","date":"2022-02-10","arxiv_id":"2202.05256","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/tasnet-surpassing-ideal-time-frequency","slug":"tasnet-surpassing-ideal-time-frequency","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","date":"2018-09-20","arxiv_id":"1809.07454","rows_on_this_dataset":1,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":36,"samples_ran":28,"samples_constructed":0,"samples_ran_checked":22,"samples_ran_instrument_failed":6,"samples_unverified":8,"pointer_only_for_licence":16,"official":{"repos":["naplab/Conv-TasNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tasnet-surpassing-ideal-time-frequency#ran","syntology_url":"https://syntology.ai/paper/1809.07454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.07454"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/investigating-training-objectives-for","slug":"investigating-training-objectives-for","title":"Investigating Training Objectives for Generative Speech Enhancement","date":"2024-09-16","arxiv_id":"2409.10753","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/schrodinger-bridge-for-generative-speech","slug":"schrodinger-bridge-for-generative-speech","title":"Schrödinger Bridge for Generative Speech Enhancement","date":"2024-07-22","arxiv_id":"2407.16074","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hybrid-transformers-for-music-source","slug":"hybrid-transformers-for-music-source","title":"Hybrid Transformers for Music Source Separation","date":"2022-11-15","arxiv_id":"2211.08553","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":1,"pointer_only_for_licence":10,"official":{"repos":["facebookresearch/demucs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/hybrid-transformers-for-music-source#ran","syntology_url":"https://syntology.ai/paper/2211.08553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08553"}}}},{"paper":"/paper/speech-enhancement-and-dereverberation-with","slug":"speech-enhancement-and-dereverberation-with","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","date":"2022-08-11","arxiv_id":"2208.05830","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/conditional-diffusion-probabilistic-model-for","slug":"conditional-diffusion-probabilistic-model-for","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","date":"2022-02-10","arxiv_id":"2202.05256","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/tasnet-surpassing-ideal-time-frequency","slug":"tasnet-surpassing-ideal-time-frequency","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","date":"2018-09-20","arxiv_id":"1809.07454","rows_on_this_dataset":1,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":36,"samples_ran":28,"samples_constructed":0,"samples_ran_checked":22,"samples_ran_instrument_failed":6,"samples_unverified":8,"pointer_only_for_licence":16,"official":{"repos":["naplab/Conv-TasNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tasnet-surpassing-ideal-time-frequency#ran","syntology_url":"https://syntology.ai/paper/1809.07454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.07454"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/ears-wham/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/ears-wham/papers/ran/1","json":"/dataset/ears-wham/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":46,"samples_ran":37,"samples_constructed":0,"samples_ran_checked":27,"samples_ran_instrument_failed":10,"samples_unverified":9,"pointer_only_for_licence":26,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"1b33160037dce31578c02a8181047e7f29cff123e738f16bbee0c4a2dac2087b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}