{"url":"/task/noisy-speech-recognition","name":"Noisy Speech Recognition","slug":"noisy-speech-recognition","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":13,"papers_with_code":3,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/noisy-speech-recognition-on-chime-real","slug":"noisy-speech-recognition-on-chime-real","dataset":"CHiME real","dataset_url":null,"rows_in_archive":5,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"Distortion-Independent + WRBN + Utterance-Wise Recurrent Dropout + Magnitude Features","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/noisy-speech-recognition-on-chime-clean","slug":"noisy-speech-recognition-on-chime-clean","dataset":"CHiME clean","dataset_url":null,"rows_in_archive":2,"metrics":["Percentage error"],"first_row_in_archive_order":{"model":"Deep Speech 2","paper_title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","paper_url":"/paper/deep-speech-2-end-to-end-speech-recognition","paper_date":"2015-12-08","arxiv_id":"1512.02595","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/deep_speech"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models"},{"title":"baidu-research/warp-ctc","url":"https://github.com/baidu-research/warp-ctc"},{"title":"SeanNaren/deepspeech.pytorch","url":"https://github.com/SeanNaren/deepspeech.pytorch"},{"title":"TensorSpeech/TensorFlowASR","url":"https://github.com/TensorSpeech/TensorFlowASR"},{"title":"DeepMark/deepmark","url":"https://github.com/DeepMark/deepmark"},{"title":"SeanNaren/deepspeech.torch","url":"https://github.com/SeanNaren/deepspeech.torch"},{"title":"robmsmt/KerasDeepSpeech","url":"https://github.com/robmsmt/KerasDeepSpeech"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/audio/deepspeech2"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/warpctc"},{"title":"msalhab96/SpeeQ","url":"https://github.com/msalhab96/SpeeQ"},{"title":"myrtleSoftware/deepspeech","url":"https://github.com/myrtleSoftware/deepspeech"},{"title":"sooftware/End-to-End-Speech-Recognition-Models","url":"https://github.com/sooftware/End-to-End-Speech-Recognition-Models"},{"title":"sooftware/OpenSpeech","url":"https://github.com/sooftware/OpenSpeech"},{"title":"victor369basu/End2EndAutomaticSpeechRecognition","url":"https://github.com/victor369basu/End2EndAutomaticSpeechRecognition"},{"title":"raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech","url":"https://github.com/raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech"},{"title":"fd873630/deep_speech_2_korean","url":"https://github.com/fd873630/deep_speech_2_korean"},{"title":"mangelroman/audio2score","url":"https://github.com/mangelroman/audio2score"},{"title":"cosmoquester/speech-recognition","url":"https://github.com/cosmoquester/speech-recognition"},{"title":"switiz/deepspeech2.pytorch","url":"https://github.com/switiz/deepspeech2.pytorch"},{"title":"bjtommychen/Keras_DeepSpeech2_SpeechRecognition","url":"https://github.com/bjtommychen/Keras_DeepSpeech2_SpeechRecognition"},{"title":"GavinGuan95/Punctuator.Pytorch","url":"https://github.com/GavinGuan95/Punctuator.Pytorch"},{"title":"MangoMoe/VerbalVim","url":"https://github.com/MangoMoe/VerbalVim"},{"title":"umd-fire-coml/2020-Speech-Recognition","url":"https://github.com/umd-fire-coml/2020-Speech-Recognition"},{"title":"hkakitani/deepspeech.pytorch","url":"https://github.com/hkakitani/deepspeech.pytorch"},{"title":"sburud/master","url":"https://gitlab.com/sburud/master"},{"title":"raraz15/DeepTurkish","url":"https://github.com/raraz15/DeepTurkish"},{"title":"UnofficialJuliaMirror/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirror/DeepMark-deepmark"},{"title":"freshtan/deepspeech2","url":"https://github.com/freshtan/deepspeech2"},{"title":"wangys102/MindSpore","url":"https://github.com/wangys102/MindSpore/tree/main/DeepSpeech2"},{"title":"2023-MindSpore-1/ms-code-63","url":"https://github.com/2023-MindSpore-1/ms-code-63"},{"title":"2023-MindSpore-1/ms-code-57","url":"https://github.com/2023-MindSpore-1/ms-code-57"},{"title":"UnofficialJuliaMirrorSnapshots/DeepMark-deepmark","url":"https://github.com/UnofficialJuliaMirrorSnapshots/DeepMark-deepmark"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/DeepSpeech2"}],"syntology":{"n":39,"n_ran":2,"n_unverified":37,"n_pointer_only":0}}}],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/speech-recognition","name":"Speech Recognition"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":3,"of":3,"tagged_in_all":13,"items":[{"url":"/paper/deep-speech-2-end-to-end-speech-recognition","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","date":"2015-12-08","arxiv_id":"1512.02595","repositories_listed":35,"syntology":{"n":39,"n_ran":2,"n_unverified":37,"n_pointer_only":0}},{"url":"/paper/the-pytorch-kaldi-speech-recognition-toolkit","title":"The PyTorch-Kaldi Speech Recognition Toolkit","date":"2018-11-19","arxiv_id":"1811.07453","repositories_listed":11,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/visual-context-driven-audio-feature","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","date":"2022-07-13","arxiv_id":"2207.06020","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}