{"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":"/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_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-pytorch-kaldi-speech-recognition-toolkit#ran","syntology_url":"https://syntology.ai/paper/1811.07453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.07453"}},"official":{"repos":["mravanelli/pytorch-kaldi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}}},{"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":30,"of":30,"of_with_code":10,"tagged_in_all":30,"counts":{"archive_papers_tagged":30,"with_a_code_link":10,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":30,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/the-pytorch-kaldi-speech-recognition-toolkit","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-pytorch-kaldi-speech-recognition-toolkit#ran","syntology_url":"https://syntology.ai/paper/1811.07453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.07453"}},"official":{"repos":["mravanelli/pytorch-kaldi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/residual-lstm-design-of-a-deep-recurrent","slug":"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","slug":"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_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meshrir-a-dataset-of-room-impulse-responses#ran","syntology_url":"https://syntology.ai/paper/2106.10801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10801"}},"official":{"repos":["sh01k/MeshRIR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-dirha-english-corpus-and-related-tasks","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":null,"slug":"the-chime-8-dasr-challenge-for-generalizable","title":"The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization","date":"2024-07-23","arxiv_id":"2407.16447","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-blind-source-separation-and","title":"Neural Blind Source Separation and Diarization for Distant Speech Recognition","date":"2024-06-12","arxiv_id":"2406.08396","repositories_listed":0,"syntology":null},{"url":"/paper/direction-aware-joint-adaptation-of-neural","slug":"direction-aware-joint-adaptation-of-neural","title":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","date":"2022-07-15","arxiv_id":"2207.07273","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-microphone-position-measurement","title":"Impact of Microphone position Measurement Error on Multi Channel Distant Speech Recognition & Intelligibility","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-large-receptive-field-convolutional","title":"Analyzing Large Receptive Field Convolutional Networks for Distant Speech Recognition","date":"2019-10-15","arxiv_id":"1910.07047","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-domain-multi-channel-acoustic","title":"Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition","date":"2019-04-28","arxiv_id":"1903.05299","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-geometry-spatial-acoustic-modeling-for","title":"Multi-Geometry Spatial Acoustic Modeling for Distant Speech Recognition","date":"2019-04-28","arxiv_id":"1903.06539","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-enhancement-augmentation-and","title":"A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition","date":"2018-06-13","arxiv_id":"1806.04841","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-context-window-composition-for","title":"Automatic context window composition for distant speech recognition","date":"2018-05-26","arxiv_id":"1805.10498","repositories_listed":0,"syntology":null},{"url":"/paper/building-state-of-the-art-distant-speech","slug":"building-state-of-the-art-distant-speech","title":"Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline","date":"2018-03-27","arxiv_id":"1803.10109","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-distant-speech-recognition","title":"Deep Learning for Distant Speech Recognition","date":"2017-12-17","arxiv_id":"1712.06086","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridgenets-student-teacher-transfer-learning","title":"BridgeNets: Student-Teacher Transfer Learning Based on Recursive Neural Networks and its Application to Distant Speech Recognition","date":"2017-10-27","arxiv_id":"1710.10224","repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-normalized-joint-training-for-dnn-based","title":"Batch-normalized joint training for DNN-based distant speech recognition","date":"2017-03-24","arxiv_id":"1703.08471","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-network-of-deep-neural-networks-for-distant","title":"A network of deep neural networks for distant speech recognition","date":"2017-03-23","arxiv_id":"1703.08002","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-attention-based-distant-speech","title":"End-to-end attention-based distant speech recognition with Highway LSTM","date":"2016-10-17","arxiv_id":"1610.05361","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-of-jointly-trained-deep-neural","title":"Ensemble of Jointly Trained Deep Neural Network-Based Acoustic Models for Reverberant Speech Recognition","date":"2016-08-17","arxiv_id":"1608.04983","repositories_listed":0,"syntology":null},{"url":null,"slug":"highway-long-short-term-memory-rnns-for","title":"Highway Long Short-Term Memory RNNs for Distant Speech Recognition","date":"2015-10-30","arxiv_id":"1510.08983","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dirha-simulated-corpus","title":"The DIRHA simulated corpus","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-sweet-home-speech-and-multimodal-corpus","title":"The Sweet-Home speech and multimodal corpus for home automation interaction","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reconnaissance-automatique-de-la-parole","title":"Reconnaissance automatique de la parole distante dans un habitat intelligent : m\\'ethodes multi-sources en conditions r\\'ealistes (Distant Speech Recognition in a Smart Home : Comparison of Several Multisource ASRs in Realistic Conditions) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"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"},"key_notes":{"n_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'","n_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_where_code_ran":2,"papers_where_code_ran_first_page":"/task/distant-speech-recognition/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/distant-speech-recognition/papers/ran/1","json":"/task/distant-speech-recognition/papers/ran/1.json","rows":2}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"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"},"record_sha256":"4213dd4c2f477c04f71eb6f95a129a1898e0779912a7311b3b7a31fa4ef38747","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}