{"url":"/task/distant-speech-recognition","name":"Distant Speech Recognition","slug":"distant-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":"archive_url"},"counts":{"papers_tagged":30,"papers_with_code":10,"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":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/distant-speech-recognition-on-dirha-english","slug":"distant-speech-recognition-on-dirha-english","dataset":"DIRHA English WSJ","dataset_url":"/dataset/dirha","rows_in_archive":3,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"Li-GRU","paper_title":"The PyTorch-Kaldi Speech Recognition Toolkit","paper_url":"/paper/the-pytorch-kaldi-speech-recognition-toolkit","paper_date":"2018-11-19","arxiv_id":"1811.07453","code_links":[{"title":"mravanelli/pytorch-kaldi","url":"https://github.com/mravanelli/pytorch-kaldi"},{"title":"wponghiran/imp-snns-for-sl","url":"https://github.com/wponghiran/imp-snns-for-sl"},{"title":"xpz123/pytorch-kaldi","url":"https://github.com/xpz123/pytorch-kaldi"},{"title":"NOEPG/pytorch-kaldi","url":"https://github.com/NOEPG/pytorch-kaldi"},{"title":"Baileyswu/pytorch-hmm-vae","url":"https://github.com/Baileyswu/pytorch-hmm-vae"},{"title":"ayyucedemirbas/gcommands_12_classes","url":"https://github.com/ayyucedemirbas/gcommands_12_classes"},{"title":"yrhvivian/pytorch-kaldi","url":"https://github.com/yrhvivian/pytorch-kaldi"},{"title":"PeiyanFlying/https-github.com-PeiyanFlying-pytorch-kaldi","url":"https://github.com/PeiyanFlying/https-github.com-PeiyanFlying-pytorch-kaldi"},{"title":"amikey/pytorch-kaldi","url":"https://github.com/amikey/pytorch-kaldi"},{"title":"Dahee96/Seq2seq-","url":"https://github.com/Dahee96/Seq2seq-"},{"title":"walterheymans/pytorch-kaldi-gan","url":"https://github.com/walterheymans/pytorch-kaldi-gan"}],"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}}},{"leaderboard":"/sota/distant-speech-recognition-on-chime-4-real","slug":"distant-speech-recognition-on-chime-4-real","dataset":"CHiME-4 real 6ch","dataset_url":null,"rows_in_archive":2,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"Complex Spectral Mapping + WRBN + Utterance-Wise Dropout + Iterative Speaker Adaptation","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/reverb-challenge","name":"ReVerb Challenge","full_name":"REverberant Voice Enhancement and Recognition Benchmark","num_papers_in_archive":55},{"url":"/dataset/dirha","name":"DIRHA","full_name":"Distant-speech Interaction for Robust Home Applications","num_papers_in_archive":19},{"url":"/dataset/dipco","name":"DiPCo","full_name":"DiPCo -- Dinner Party Corpus","num_papers_in_archive":16},{"url":"/dataset/berst","name":"BERSt","full_name":"Basic Emotion Random phrase Shouts","num_papers_in_archive":1}],"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":10,"of":10,"tagged_in_all":30,"items":[{"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/residual-lstm-design-of-a-deep-recurrent","title":"Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition","date":"2017-01-10","arxiv_id":"1701.03360","repositories_listed":3,"syntology":null},{"url":"/paper/meshrir-a-dataset-of-room-impulse-responses","title":"MeshRIR: A Dataset of Room Impulse Responses on Meshed Grid Points For Evaluating Sound Field Analysis and Synthesis Methods","date":"2021-06-21","arxiv_id":"2106.10801","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/the-dirha-english-corpus-and-related-tasks","title":"The DIRHA-English corpus and related tasks for distant-speech recognition in domestic environments","date":"2017-10-06","arxiv_id":"1710.02560","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-rank-microphones-for-distant","title":"Learning to Rank Microphones for Distant Speech Recognition","date":"2021-04-06","arxiv_id":"2104.02819","repositories_listed":1,"syntology":null},{"url":"/paper/quaternion-neural-networks-for-multi-channel","title":"Quaternion Neural Networks for Multi-channel Distant Speech Recognition","date":"2020-05-18","arxiv_id":"2005.08566","repositories_listed":1,"syntology":null},{"url":"/paper/learning-problem-agnostic-speech","title":"Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks","date":"2019-04-06","arxiv_id":"1904.03416","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-convolutional-filters-with","title":"Interpretable Convolutional Filters with SincNet","date":"2018-11-23","arxiv_id":"1811.09725","repositories_listed":1,"syntology":null},{"url":"/paper/contaminated-speech-training-methods-for","title":"Contaminated speech training methods for robust DNN-HMM distant speech recognition","date":"2017-10-10","arxiv_id":"1710.03538","repositories_listed":1,"syntology":null},{"url":"/paper/open-source-german-distant-speech-recognition","title":"Open Source German Distant Speech Recognition: Corpus and Acoustic Model","date":"2015-12-11","arxiv_id":null,"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"}}