{"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/2000-hub5-english","name":"2000 HUB5 English","full_name":"2000 HUB5 English","description_markdown":"**2000 HUB5 English Evaluation Transcripts** was developed by the Linguistic Data Consortium (LDC)  and consists of transcripts of 40 English telephone conversations used in the 2000 HUB5 evaluation sponsored by NIST (National Institute of Standards and Technology). \r\n\r\nThe Hub5 evaluation series focused on conversational speech over the telephone with the particular task of transcribing conversational speech into text. Its goals were to explore promising new areas in the recognition of conversational speech, to develop advanced technology incorporating those ideas and to measure the performance of new technology.","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC2002T43","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Hub5'00 SwitchBoard","2000 HUB5 English","SWBD Eval2000"],"data_loaders":[],"num_papers_in_archive":33,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-recognition-on-hub500-switchboard","task":"Speech Recognition","dataset_variant":"Hub5'00 SwitchBoard","rows":5,"metrics":["SwitchBoard","CallHome","Eval2000","Hub5'00"],"first_row_in_archive_order":{"model":"LAS + SpecAugment (with LM, Switchboard mild policy)","paper":"/paper/specaugment-a-simple-data-augmentation-method","metrics":{"CallHome":"14.6","SwitchBoard":"6.8"},"code_links":[{"title":"mozilla/DeepSpeech","url":"https://github.com/mozilla/DeepSpeech"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"makcedward/nlpaug","url":"https://github.com/makcedward/nlpaug"},{"title":"iver56/audiomentations","url":"https://github.com/iver56/audiomentations"},{"title":"shelling203/SpecAugment","url":"https://github.com/shelling203/SpecAugment"},{"title":"DemisEom/SpecAugment","url":"https://github.com/DemisEom/SpecAugment"},{"title":"google-research/leaf-audio","url":"https://github.com/google-research/leaf-audio"},{"title":"ZhengkunTian/OpenTransformer","url":"https://github.com/ZhengkunTian/OpenTransformer"},{"title":"lRomul/argus-freesound","url":"https://github.com/lRomul/argus-freesound"},{"title":"shuaijiang/Whisper-Finetune","url":"https://github.com/shuaijiang/Whisper-Finetune"},{"title":"ebouteillon/freesound-audio-tagging-2019","url":"https://github.com/ebouteillon/freesound-audio-tagging-2019"},{"title":"SarthakYadav/audax","url":"https://github.com/SarthakYadav/audax"},{"title":"freds0/data_augmentation_for_asr","url":"https://github.com/freds0/data_augmentation_for_asr"},{"title":"biyoml/End-to-End-Mandarin-ASR","url":"https://github.com/biyoml/End-to-End-Mandarin-ASR"},{"title":"jackjhliu/End-to-End-Mandarin-ASR","url":"https://github.com/jackjhliu/End-to-End-Mandarin-ASR"},{"title":"KimJeongSun/SpecAugment_numpy_scipy","url":"https://github.com/KimJeongSun/SpecAugment_numpy_scipy"},{"title":"AmirmohammadRostami/KeywordsSpotting-EfficientNet-A0","url":"https://github.com/AmirmohammadRostami/KeywordsSpotting-EfficientNet-A0"},{"title":"sh951011/Korean-Speech-Recognition","url":"https://github.com/sh951011/Korean-Speech-Recognition/blob/master/package/feature.py"},{"title":"hgstudent/las","url":"https://github.com/hgstudent/las"},{"title":"audio-westlakeu/rct","url":"https://github.com/audio-westlakeu/rct"},{"title":"Audio-WestlakeU/RCT-Random-Consistency-Training","url":"https://github.com/Audio-WestlakeU/RCT-Random-Consistency-Training"},{"title":"HLasse/wav2vec_finetune","url":"https://github.com/HLasse/wav2vec_finetune"},{"title":"park-cheol/ASR-Conformer","url":"https://github.com/park-cheol/ASR-Conformer"},{"title":"cosmoquester/speech-recognition","url":"https://github.com/cosmoquester/speech-recognition"},{"title":"MichaelisTrofficus/spec_augment","url":"https://github.com/MichaelisTrofficus/spec_augment"},{"title":"viig99/mixmatch-freesound","url":"https://github.com/viig99/mixmatch-freesound"},{"title":"HeleneFabia/keyword-spotter","url":"https://github.com/HeleneFabia/keyword-spotter"},{"title":"andychinka/dcase-challenge","url":"https://github.com/andychinka/dcase-challenge"},{"title":"ahmedalbahnasawy/spec_torch_kaldi-compatibility","url":"https://github.com/ahmedalbahnasawy/spec_torch_kaldi-compatibility"},{"title":"kimjeongsun/specaugment","url":"https://github.com/kimjeongsun/specaugment"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-modelling-on-2000-hub5-english","task":"Language Modelling","dataset_variant":"2000 HUB5 English","rows":1,"metrics":["10-stage average accuracy"],"first_row_in_archive_order":{"model":"MMLU","paper":"/paper/spirit-lm-interleaved-spoken-and-written","metrics":{"10-stage average accuracy":"10"},"code_links":[{"title":"facebookresearch/spiritlm","url":"https://github.com/facebookresearch/spiritlm"}]},"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":5,"of":5,"counts":{"papers_with_a_benchmark_row":5,"with_a_code_link":5,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/spirit-lm-interleaved-spoken-and-written","slug":"spirit-lm-interleaved-spoken-and-written","title":"Spirit LM: Interleaved Spoken and Written Language Model","date":"2024-02-08","arxiv_id":"2402.05755","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/spiritlm"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spirit-lm-interleaved-spoken-and-written#ran","syntology_url":"https://syntology.ai/paper/2402.05755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05755"}}}},{"paper":"/paper/cat-a-ctc-crf-based-asr-toolkit-bridging-the","slug":"cat-a-ctc-crf-based-asr-toolkit-bridging-the","title":"CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency","date":"2020-05-27","arxiv_id":"2005.13326","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/espresso-a-fast-end-to-end-neural-speech","slug":"espresso-a-fast-end-to-end-neural-speech","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","date":"2019-09-18","arxiv_id":"1909.08723","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["freewym/espresso"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/espresso-a-fast-end-to-end-neural-speech#ran","syntology_url":"https://syntology.ai/paper/1909.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08723"}}}},{"paper":"/paper/specaugment-a-simple-data-augmentation-method","slug":"specaugment-a-simple-data-augmentation-method","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","date":"2019-04-18","arxiv_id":"1904.08779","rows_on_this_dataset":2,"code_links":30,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/specaugment-a-simple-data-augmentation-method#ran","syntology_url":"https://syntology.ai/paper/1904.08779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08779"}}}},{"paper":"/paper/jasper-an-end-to-end-convolutional-neural","slug":"jasper-an-end-to-end-convolutional-neural","title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","date":"2019-04-05","arxiv_id":"1904.03288","rows_on_this_dataset":1,"code_links":10,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/spirit-lm-interleaved-spoken-and-written","slug":"spirit-lm-interleaved-spoken-and-written","title":"Spirit LM: Interleaved Spoken and Written Language Model","date":"2024-02-08","arxiv_id":"2402.05755","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/spiritlm"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spirit-lm-interleaved-spoken-and-written#ran","syntology_url":"https://syntology.ai/paper/2402.05755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05755"}}}},{"paper":"/paper/cat-a-ctc-crf-based-asr-toolkit-bridging-the","slug":"cat-a-ctc-crf-based-asr-toolkit-bridging-the","title":"CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency","date":"2020-05-27","arxiv_id":"2005.13326","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/espresso-a-fast-end-to-end-neural-speech","slug":"espresso-a-fast-end-to-end-neural-speech","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","date":"2019-09-18","arxiv_id":"1909.08723","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["freewym/espresso"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/espresso-a-fast-end-to-end-neural-speech#ran","syntology_url":"https://syntology.ai/paper/1909.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08723"}}}},{"paper":"/paper/specaugment-a-simple-data-augmentation-method","slug":"specaugment-a-simple-data-augmentation-method","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","date":"2019-04-18","arxiv_id":"1904.08779","rows_on_this_dataset":2,"code_links":30,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":18,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/specaugment-a-simple-data-augmentation-method#ran","syntology_url":"https://syntology.ai/paper/1904.08779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08779"}}}},{"paper":"/paper/jasper-an-end-to-end-convolutional-neural","slug":"jasper-an-end-to-end-convolutional-neural","title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","date":"2019-04-05","arxiv_id":"1904.03288","rows_on_this_dataset":1,"code_links":10,"syntology":null}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/2000-hub5-english/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/2000-hub5-english/papers/ran/1","json":"/dataset/2000-hub5-english/papers/ran/1.json","rows":3}],"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":3,"samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":2,"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":"907c388804d22546734cad4d342af11e6e6369412ae19bf58ff360e70fa21f13","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}