{"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/librimix","name":"LibriMix","full_name":null,"description_markdown":"LibriMix is an open-source alternative to wsj0-2mix. Based on LibriSpeech, LibriMix consists of two- or three-speaker mixtures combined with ambient noise samples from WHAM!. \r\n\r\nSource: [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](/paper/librimix-an-open-source-dataset-for)","description_withheld":null,"homepage":"https://github.com/JorisCos/LibriMix","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/librimix-an-open-source-dataset-for","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","first_author":null,"url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Enhancement","url":"/task/speech-enhancement","datasets_with_task":"/datasets/task/speech-enhancement"},{"name":"Speech Separation","url":"/task/speech-separation","datasets_with_task":"/datasets/task/speech-separation"},{"name":"Audio Source Separation","url":"/task/audio-source-separation","datasets_with_task":"/datasets/task/audio-source-separation"}],"languages":[],"variants":["LibriMix","Libri2Mix"],"data_loaders":[{"repo":"https://github.com/JorisCos/LibriMix","url":"https://github.com/JorisCos/LibriMix","frameworks":[]}],"num_papers_in_archive":122,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-separation-on-libri2mix","task":"Speech Separation","dataset_variant":"Libri2Mix","rows":10,"metrics":["SI-SDRi","SDRi","Number of parameters (M)","SDR"],"first_row_in_archive_order":{"model":"MossFormer2 (w speed perturb)","paper":"/paper/mossformer2-combining-transformer-and-rnn-1","metrics":{"SI-SDRi":"22.2"},"code_links":[{"title":"modelscope/ClearerVoice-Studio","url":"https://github.com/modelscope/ClearerVoice-Studio"},{"title":"alibabasglab/MossFormer2","url":"https://github.com/alibabasglab/MossFormer2"}]},"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":4,"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/wanna-hear-your-voice-adaptive-effective-and","slug":"wanna-hear-your-voice-adaptive-effective-and","title":"Wanna hear your voice? A sample is all we need!","date":"2024-10-01","arxiv_id":"2410.00527","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tf-locoformer-transformer-with-local-modeling","slug":"tf-locoformer-transformer-with-local-modeling","title":"TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement","date":"2024-08-06","arxiv_id":"2408.03440","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/separate-and-diffuse-using-a-pretrained","slug":"separate-and-diffuse-using-a-pretrained","title":"Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation","date":"2023-01-25","arxiv_id":"2301.10752","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/an-efficient-encoder-decoder-architecture","slug":"an-efficient-encoder-decoder-architecture","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","date":"2022-09-30","arxiv_id":"2209.15200","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":13,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":4,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["JusperLee/TDANet"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-efficient-encoder-decoder-architecture#ran","syntology_url":"https://syntology.ai/paper/2209.15200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.15200"}}}},{"paper":"/paper/self-supervised-pre-training-reduces-label","slug":"self-supervised-pre-training-reduces-label","title":"Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training","date":"2020-10-29","arxiv_id":"2010.15366","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/mossformer2-combining-transformer-and-rnn-1","slug":"mossformer2-combining-transformer-and-rnn-1","title":"MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation","date":null,"arxiv_id":"2312.11825","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["modelscope/ClearerVoice-Studio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mossformer2-combining-transformer-and-rnn-1#ran","syntology_url":"https://syntology.ai/paper/2312.11825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11825"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/wanna-hear-your-voice-adaptive-effective-and","slug":"wanna-hear-your-voice-adaptive-effective-and","title":"Wanna hear your voice? A sample is all we need!","date":"2024-10-01","arxiv_id":"2410.00527","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tf-locoformer-transformer-with-local-modeling","slug":"tf-locoformer-transformer-with-local-modeling","title":"TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement","date":"2024-08-06","arxiv_id":"2408.03440","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/separate-and-diffuse-using-a-pretrained","slug":"separate-and-diffuse-using-a-pretrained","title":"Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation","date":"2023-01-25","arxiv_id":"2301.10752","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/an-efficient-encoder-decoder-architecture","slug":"an-efficient-encoder-decoder-architecture","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","date":"2022-09-30","arxiv_id":"2209.15200","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":13,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":4,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["JusperLee/TDANet"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-efficient-encoder-decoder-architecture#ran","syntology_url":"https://syntology.ai/paper/2209.15200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.15200"}}}},{"paper":"/paper/self-supervised-pre-training-reduces-label","slug":"self-supervised-pre-training-reduces-label","title":"Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training","date":"2020-10-29","arxiv_id":"2010.15366","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/mossformer2-combining-transformer-and-rnn-1","slug":"mossformer2-combining-transformer-and-rnn-1","title":"MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation","date":null,"arxiv_id":"2312.11825","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["modelscope/ClearerVoice-Studio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mossformer2-combining-transformer-and-rnn-1#ran","syntology_url":"https://syntology.ai/paper/2312.11825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11825"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/librimix/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/librimix/papers/ran/1","json":"/dataset/librimix/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":22,"samples_ran":17,"samples_constructed":8,"samples_ran_checked":12,"samples_ran_instrument_failed":5,"samples_unverified":5,"pointer_only_for_licence":2,"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":"4ede6615fa3e10b83fd3f45db9020ed67fa32b0fc82e6601523fbb615cd16cd5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}