{"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/robust-speech-recognition","name":"Robust Speech Recognition","slug":"robust-speech-recognition","description_markdown":null,"categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Music","url":"/area/music"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"},{"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":97,"papers_with_code":26,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":[],"datasets":[{"url":"/dataset/dipco","name":"DiPCo","full_name":"DiPCo -- Dinner Party Corpus","num_papers_in_archive":16},{"url":"/dataset/google-speech-commands-musan","name":"Google Speech Commands - Musan","full_name":"","num_papers_in_archive":3},{"url":"/dataset/fsc-p2","name":"FSC-P2","full_name":"Fearless Steps Challenge Phase2","num_papers_in_archive":1},{"url":"/dataset/speech-robust-bench","name":"Speech Robust Bench","full_name":"","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":97,"of":97,"of_with_code":26,"tagged_in_all":97,"counts":{"archive_papers_tagged":97,"with_a_code_link":26,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":97,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/robust-speech-recognition-via-large-scale-1","slug":"robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","date":"2022-12-06","arxiv_id":"2212.04356","repositories_listed":15,"syntology":{"n":59,"n_ran":49,"n_constructed":0,"n_ran_checked":36,"n_instrument":13,"n_unverified":10,"n_honours":4,"n_violates":1,"n_no_contract":31,"n_pointer_only":21,"phrase":"49 ran (of which 0 constructed an object rather than computing a result; 36 with no instrument failure: 4 honoured, 1 violated, 31 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/robust-speech-recognition-via-large-scale-1#ran","syntology_url":"https://syntology.ai/paper/2212.04356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04356"}},"official":{"repos":["openai/whisper"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/interactive-feature-fusion-for-end-to-end","slug":"interactive-feature-fusion-for-end-to-end","title":"Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition","date":"2021-10-11","arxiv_id":"2110.05267","repositories_listed":2,"syntology":null},{"url":"/paper/scalable-factorized-hierarchical-variational","slug":"scalable-factorized-hierarchical-variational","title":"Scalable Factorized Hierarchical Variational Autoencoder Training","date":"2018-04-09","arxiv_id":"1804.03201","repositories_listed":2,"syntology":null},{"url":"/paper/very-deep-convolutional-neural-networks-for-1","slug":"very-deep-convolutional-neural-networks-for-1","title":"Very Deep Convolutional Neural Networks for Robust Speech Recognition","date":"2016-10-02","arxiv_id":"1610.00277","repositories_listed":2,"syntology":null},{"url":"/paper/dysarthria-normalization-via-local-lie-group","slug":"dysarthria-normalization-via-local-lie-group","title":"Dysarthria Normalization via Local Lie Group Transformations for Robust ASR","date":"2025-04-16","arxiv_id":"2504.12279","repositories_listed":1,"syntology":null},{"url":"/paper/mms-llama-efficient-llm-based-audio-visual-1","slug":"mms-llama-efficient-llm-based-audio-visual-1","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","date":"2025-03-14","arxiv_id":"2503.11315","repositories_listed":1,"syntology":null},{"url":"/paper/mwhisper-flamingo-for-multilingual-audio","slug":"mwhisper-flamingo-for-multilingual-audio","title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition","date":"2025-02-03","arxiv_id":"2502.01547","repositories_listed":1,"syntology":null},{"url":"/paper/channel-aware-domain-adaptive-generative","slug":"channel-aware-domain-adaptive-generative","title":"Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition","date":"2024-09-19","arxiv_id":"2409.12386","repositories_listed":1,"syntology":null},{"url":"/paper/speech-robust-bench-a-robustness-benchmark","slug":"speech-robust-bench-a-robustness-benchmark","title":"Speech Robust Bench: A Robustness Benchmark For Speech Recognition","date":"2024-03-08","arxiv_id":"2403.07937","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/speech-robust-bench-a-robustness-benchmark#ran","syntology_url":"https://syntology.ai/paper/2403.07937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07937"}},"official":{"repos":["ahmedshah1494/speech_robust_bench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/large-language-models-are-efficient-learners","slug":"large-language-models-are-efficient-learners","title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","date":"2024-01-19","arxiv_id":"2401.10446","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-are-efficient-learners#ran","syntology_url":"https://syntology.ai/paper/2401.10446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10446"}},"official":{"repos":["yuchen005/robustger"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lyricwhiz-robust-multilingual-zero-shot","slug":"lyricwhiz-robust-multilingual-zero-shot","title":"LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT","date":"2023-06-29","arxiv_id":"2306.17103","repositories_listed":1,"syntology":null},{"url":"/paper/muavic-a-multilingual-audio-visual-corpus-for","slug":"muavic-a-multilingual-audio-visual-corpus-for","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","date":"2023-03-01","arxiv_id":"2303.00628","repositories_listed":1,"syntology":null},{"url":"/paper/gradient-remedy-for-multi-task-learning-in","slug":"gradient-remedy-for-multi-task-learning-in","title":"Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition","date":"2023-02-22","arxiv_id":"2302.11362","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-efficient-conformer-for-robust","slug":"audio-visual-efficient-conformer-for-robust","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","date":"2023-01-04","arxiv_id":"2301.01456","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/audio-visual-efficient-conformer-for-robust#ran","syntology_url":"https://syntology.ai/paper/2301.01456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.01456"}},"official":{"repos":["burchim/avec"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ccc-wav2vec-2-0-clustering-aided-cross","slug":"ccc-wav2vec-2-0-clustering-aided-cross","title":"CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representations","date":"2022-10-05","arxiv_id":"2210.02592","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":2,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ccc-wav2vec-2-0-clustering-aided-cross#ran","syntology_url":"https://syntology.ai/paper/2210.02592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02592"}},"official":{"repos":["speech-lab-iitm/ccc-wav2vec-2.0"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dent-ddsp-data-efficient-noisy-speech","slug":"dent-ddsp-data-efficient-noisy-speech","title":"DENT-DDSP: Data-efficient noisy speech generator using differentiable digital signal processors for explicit distortion modelling and noise-robust speech recognition","date":"2022-08-01","arxiv_id":"2208.00987","repositories_listed":1,"syntology":null},{"url":"/paper/espnet-se-speech-enhancement-for-robust","slug":"espnet-se-speech-enhancement-for-robust","title":"ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding","date":"2022-07-19","arxiv_id":"2207.09514","repositories_listed":1,"syntology":null},{"url":"/paper/dual-path-style-learning-for-end-to-end-noise","slug":"dual-path-style-learning-for-end-to-end-noise","title":"Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition","date":"2022-03-28","arxiv_id":"2203.14838","repositories_listed":1,"syntology":null},{"url":"/paper/speech-enhanced-and-noise-aware-networks-for","slug":"speech-enhanced-and-noise-aware-networks-for","title":"Speech-enhanced and Noise-aware Networks for Robust Speech Recognition","date":"2022-03-25","arxiv_id":"2203.13696","repositories_listed":1,"syntology":null},{"url":"/paper/sequential-randomized-smoothing-for-1","slug":"sequential-randomized-smoothing-for-1","title":"Sequential Randomized Smoothing for Adversarially Robust Speech Recognition","date":"2021-11-05","arxiv_id":"2112.03000","repositories_listed":1,"syntology":null},{"url":"/paper/an-investigation-of-end-to-end-models-for","slug":"an-investigation-of-end-to-end-models-for","title":"An Investigation of End-to-End Models for Robust Speech Recognition","date":"2021-02-11","arxiv_id":"2102.06237","repositories_listed":1,"syntology":null},{"url":"/paper/domain-adaptation-using-class-similarity-for","slug":"domain-adaptation-using-class-similarity-for","title":"Domain Adaptation Using Class Similarity for Robust Speech Recognition","date":"2020-11-05","arxiv_id":"2011.02782","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-self-supervised-learning-for-1","slug":"multi-task-self-supervised-learning-for-1","title":"Multi-task self-supervised learning for Robust Speech Recognition","date":"2020-01-25","arxiv_id":"2001.09239","repositories_listed":1,"syntology":null},{"url":"/paper/parzen-filters-for-spectral-decomposition-of","slug":"parzen-filters-for-spectral-decomposition-of","title":"Learning Waveform-Based Acoustic Models using Deep Variational Convolutional Neural Networks","date":"2019-06-23","arxiv_id":"1906.09526","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-speech-domain-adaptation-based","slug":"unsupervised-speech-domain-adaptation-based","title":"Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition","date":"2019-04-12","arxiv_id":"1904.06086","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-generative-adversarial-networks","slug":"investigating-generative-adversarial-networks","title":"Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition","date":"2018-03-27","arxiv_id":"1803.10132","repositories_listed":1,"syntology":null},{"url":null,"slug":"simclass-a-classroom-speech-dataset-generated","title":"SimClass: A Classroom Speech Dataset Generated via Game Engine Simulation For Automatic Speech Recognition Research","date":"2025-06-10","arxiv_id":"2506.09206","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speech-recognition-with-schrodinger","title":"Robust Speech Recognition with Schrödinger Bridge-Based Speech Enhancement","date":"2025-05-07","arxiv_id":"2505.04237","repositories_listed":0,"syntology":null},{"url":null,"slug":"mohave-mixture-of-hierarchical-audio-visual","title":"MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition","date":"2025-02-11","arxiv_id":"2502.10447","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-mispronunciation-pattern","title":"Data-Driven Mispronunciation Pattern Discovery for Robust Speech Recognition","date":"2025-02-01","arxiv_id":"2502.00583","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-edge-speech-understanding","title":"Privacy-Preserving Edge Speech Understanding with Tiny Foundation Models","date":"2025-01-29","arxiv_id":"2502.01649","repositories_listed":0,"syntology":null},{"url":null,"slug":"paraformer-v2-an-improved-non-autoregressive","title":"Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition","date":"2024-09-26","arxiv_id":"2409.17746","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-audiovisual-speech-recognition-models","title":"Robust Audiovisual Speech Recognition Models with Mixture-of-Experts","date":"2024-09-19","arxiv_id":"2409.12370","repositories_listed":0,"syntology":null},{"url":null,"slug":"cpt-boosted-wav2vec2-0-towards-noise-robust","title":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments","date":"2024-09-13","arxiv_id":"2409.14494","repositories_listed":0,"syntology":null},{"url":null,"slug":"xlavs-r-cross-lingual-audio-visual-speech","title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception","date":"2024-03-21","arxiv_id":"2403.14402","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-audio-visual-speech-recognition","title":"Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer","date":"2024-03-14","arxiv_id":"2405.12983","repositories_listed":0,"syntology":null},{"url":null,"slug":"kinspeak-improving-speech-recognition-for","title":"KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods","date":"2023-08-23","arxiv_id":"2308.11863","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-chime-7-dasr-challenge-distant-meeting","title":"The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios","date":"2023-06-23","arxiv_id":"2306.13734","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-beamformer-exploiting-non","title":"Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition","date":"2023-06-13","arxiv_id":"2306.07562","repositories_listed":0,"syntology":null},{"url":null,"slug":"rescuespeech-a-german-corpus-for-speech","title":"RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain","date":"2023-06-06","arxiv_id":"2306.04054","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-l2-phonemes-using-articulatory","title":"Incorporating L2 Phonemes Using Articulatory Features for Robust Speech Recognition","date":"2023-06-05","arxiv_id":"2306.02534","repositories_listed":0,"syntology":null},{"url":null,"slug":"avformer-injecting-vision-into-frozen-speech","title":"AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR","date":"2023-03-29","arxiv_id":"2303.16501","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmct-patched-multi-condition-training-for","title":"pMCT: Patched Multi-Condition Training for Robust Speech Recognition","date":"2022-07-11","arxiv_id":"2207.04949","repositories_listed":0,"syntology":null},{"url":null,"slug":"rusavic-corpus-russian-audio-visual-speech-in","title":"RUSAVIC Corpus: Russian Audio-Visual Speech in Cars","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-monoaural-speech-enhancement-for-automatic","title":"On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training","date":"2022-05-03","arxiv_id":"2205.01751","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-integration-of-speech-recognition","title":"End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation","date":"2022-04-01","arxiv_id":"2204.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-confidence-gates-for-joint-training","title":"Multiple Confidence Gates For Joint Training Of SE And ASR","date":"2022-04-01","arxiv_id":"2204.00226","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-robust-speech-recognition-with-10","title":"Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data","date":"2022-03-29","arxiv_id":"2203.15321","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-based-discriminative-autoencoders-for","title":"Chain-based Discriminative Autoencoders for Speech Recognition","date":"2022-03-25","arxiv_id":"2203.13687","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-densely-connected","title":"Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition","date":"2021-12-19","arxiv_id":"2112.10108","repositories_listed":0,"syntology":null},{"url":null,"slug":"phone-based-keyword-spotting-for-transcribing","title":"Phone Based Keyword Spotting for Transcribing Very Low Resource Languages","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-streaming-models-and-data","title":"A comparison of streaming models and data augmentation methods for robust speech recognition","date":"2021-11-19","arxiv_id":"2111.10043","repositories_listed":0,"syntology":null},{"url":null,"slug":"wav2vec-switch-contrastive-learning-from","title":"Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition","date":"2021-10-11","arxiv_id":"2110.04934","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimized-power-normalized-cepstral","title":"Optimized Power Normalized Cepstral Coefficients towards Robust Deep Speaker Verification","date":"2021-09-24","arxiv_id":"2109.12058","repositories_listed":0,"syntology":null},{"url":null,"slug":"hmm-based-phoneme-speech-recognition-system-1","title":"HMM-based phoneme speech recognition system for the control and command of industrial robots","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aphasic-speech-recognition-using-a-mixture-of","title":"Aphasic Speech Recognition using a Mixture of Speech Intelligibility Experts","date":"2020-08-25","arxiv_id":"2008.10788","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-dereverberation-of","title":"Deep Learning Based Dereverberation of Temporal Envelopesfor Robust Speech Recognition","date":"2020-08-07","arxiv_id":"2008.03339","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentive-fusion-enhanced-audio-visual","title":"Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition","date":"2020-08-06","arxiv_id":"2008.02686","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-staged-cross-lingual-acoustic-model","title":"Multi-Staged Cross-Lingual Acoustic Model Adaption for Robust Speech Recognition in Real-World Applications - A Case Study on German Oral History Interviews","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-octave-convolutions-for-robust","title":"Multi-scale Octave Convolutions for Robust Speech Recognition","date":"2019-10-31","arxiv_id":"1910.14443","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-speech-enhancement-of-publicly-available","title":"Does Speech enhancement of publicly available data help build robust Speech Recognition Systems?","date":"2019-10-29","arxiv_id":"1910.13488","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-expansion-in-dnn-based-acoustic-models","title":"Domain Expansion in DNN-based Acoustic Models for Robust Speech Recognition","date":"2019-10-01","arxiv_id":"1910.00565","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-with-augmented-synthesized","title":"Speech Recognition with Augmented Synthesized Speech","date":"2019-09-25","arxiv_id":"1909.11699","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-staged-acoustic-modeling-adaption-for","title":"Two-Staged Acoustic Modeling Adaption for Robust Speech Recognition by the Example of German Oral History Interviews","date":"2019-08-19","arxiv_id":"1908.06709","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-combining-features-for-single-channel","title":"On combining features for single-channel robust speech recognition in reverberant environments","date":"2019-06-17","arxiv_id":"1906.07299","repositories_listed":0,"syntology":null},{"url":null,"slug":"cumulative-adaptation-for-blstm-acoustic","title":"Cumulative Adaptation for BLSTM Acoustic Models","date":"2019-06-14","arxiv_id":"1906.06207","repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-attention-for-end-to-end-audio","title":"Modality Attention for End-to-End Audio-visual Speech Recognition","date":"2018-11-13","arxiv_id":"1811.05250","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-speech","title":"Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition","date":"2018-11-10","arxiv_id":"1811.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-noise-invariant-representations-for-1","title":"Learning Noise-Invariant Representations for Robust Speech Recognition","date":"2018-10-02","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-by-adversarial","title":"Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition","date":"2018-07-30","arxiv_id":"1807.11284","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-noise-invariant-representations-for","title":"Learning Noise-Invariant Representations for Robust Speech Recognition","date":"2018-07-17","arxiv_id":"1807.06610","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-augmentation-with-adversarial","title":"Training Augmentation with Adversarial Examples for Robust Speech Recognition","date":"2018-06-07","arxiv_id":"1806.02782","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-pronunciation-modeling-of-swiss","title":"Data-Driven Pronunciation Modeling of Swiss German Dialectal Speech for Automatic Speech Recognition","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-transcription-and-indexing-of-oral","title":"Improved Transcription and Indexing of Oral History Interviews for Digital Humanities Research","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spectral-feature-mapping-with-mimic-loss-for","title":"Spectral feature mapping with mimic loss for robust speech recognition","date":"2018-03-26","arxiv_id":"1803.09816","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-long-short-term-memory-adaptive","title":"Deep Long Short-Term Memory Adaptive Beamforming Networks For Multichannel Robust Speech Recognition","date":"2017-11-21","arxiv_id":"1711.08016","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-adaptation-with-domain","title":"Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition","date":"2017-11-21","arxiv_id":"1711.08010","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-speech-enhancement-with-generative","title":"Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition","date":"2017-11-15","arxiv_id":"1711.05747","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speech-recognition-using-generative","title":"Robust Speech Recognition Using Generative Adversarial Networks","date":"2017-11-05","arxiv_id":"1711.01567","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-for-robust","title":"Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation","date":"2017-07-19","arxiv_id":"1707.06265","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-environmentally-robust","title":"Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments","date":"2017-05-30","arxiv_id":"1705.10874","repositories_listed":0,"syntology":null},{"url":null,"slug":"environmental-noise-embeddings-for-robust","title":"Environmental Noise Embeddings for Robust Speech Recognition","date":"2016-01-11","arxiv_id":"1601.02553","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-modulation-spectrum","title":"調變頻譜分解技術於強健語音辨識之研究 (Investigating Modulation Spectrum Factorization Techniques for Robust Speech Recognition) [In Chinese]","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-models-for-auditory-attention-in","title":"Recurrent Models for Auditory Attention in Multi-Microphone Distance Speech Recognition","date":"2015-11-19","arxiv_id":"1511.06407","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-using-neural","title":"類神經網路訓練結合環境群集及專家混合系統於強健性語音辨識(Automatic Speech Recognition using Neural Network based Acoustic Model with the Environment Clustering and Mixture of Experts Algorithms) [In Chinese]","date":"2015-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"several-refinements-of-modulation-spectrum","title":"調變頻譜分解之改良於強健性語音辨識(Several Refinements of Modulation Spectrum Factorization for Robust Speech Recognition) [In Chinese]","date":"2015-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speech-recognition-using-consensus","title":"Robust speech recognition using consensus function based on multi-layer networks","date":"2015-07-22","arxiv_id":"1507.06023","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-normalisation-for-robust-speech","title":"Feature Normalisation for Robust Speech Recognition","date":"2015-07-14","arxiv_id":"1507.04019","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-use-of-different-feature-extraction","title":"On the Use of Different Feature Extraction Methods for Linear and Non Linear kernels","date":"2014-06-27","arxiv_id":"1406.7314","repositories_listed":0,"syntology":null},{"url":null,"slug":"employing-linear-prediction-coding-in-feature","title":"雜訊環境下應用線性估測編碼於特徵時序列之強健性語音辨識 (Employing Linear Prediction Coding in Feature Time Sequences for Robust Speech Recognition in Noisy Environments) [In Chinese]","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bayesian-network-view-on-acoustic-model","title":"A Bayesian Network View on Acoustic Model-Based Techniques for Robust Speech Recognition","date":"2013-10-11","arxiv_id":"1310.3099","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-modulation-spectrum-histogram","title":"改良調變頻譜統計圖等化法於強健性語音辨識之研究 (Improved Modulation Spectrum Histogram Equalization for Robust Speech Recognition) [In Chinese]","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sub-band-modulation-spectrum-factorization-in","title":"分頻式調變頻譜分解於強健性語音辨識 (Sub-band modulation spectrum factorization in robust speech recognition) [In Chinese]","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-learning-with-gaussian-restricted","title":"Feature Learning with Gaussian Restricted Boltzmann Machine for Robust Speech Recognition","date":"2013-09-23","arxiv_id":"1309.6176","repositories_listed":0,"syntology":null},{"url":null,"slug":"modified-splice-and-its-extension-to-non","title":"Modified SPLICE and its Extension to Non-Stereo Data for Noise Robust Speech Recognition","date":"2013-07-15","arxiv_id":"1307.4048","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-modeling-towards-robust","title":"Speech Enhancement Modeling Towards Robust Speech Recognition System","date":"2013-05-07","arxiv_id":"1305.1426","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-histogram-equalization-methods-for","title":"改良式統計圖等化法強鍵性語音辨識之研究 (Improved Histogram Equalization Methods for Robust Speech Recognition) [In Chinese]","date":"2012-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":5,"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":5,"papers_where_code_ran_first_page":"/task/robust-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/robust-speech-recognition/papers/ran/1","json":"/task/robust-speech-recognition/papers/ran/1.json","rows":5}],"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":"c7eec06b462b3249d26e0f62ded2bd9af349550e282b11001a9cd6d100c765b6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}