{"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_with_a_benchmark_row":[{"paper":"/paper/spirit-lm-interleaved-spoken-and-written","title":"Spirit LM: Interleaved Spoken and Written Language Model","date":"2024-02-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/espresso-a-fast-end-to-end-neural-speech","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","date":"2019-09-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/specaugment-a-simple-data-augmentation-method","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","date":"2019-04-18","rows_on_this_dataset":2,"code_links":30,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":1,"samples_unverified":17,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/jasper-an-end-to-end-convolutional-neural","title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","date":"2019-04-05","rows_on_this_dataset":1,"code_links":10,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":20,"samples_ran":3,"samples_unverified":17,"pointer_only_for_licence":2,"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."}