{"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/automatic-speech-recognition/papers/4","list_of":"/task/automatic-speech-recognition","task":"Automatic Speech Recognition (ASR)","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":31,"rows_per_page":100,"rows":[301,400],"of":3012,"counts":{"archive_papers_tagged":3012,"with_a_code_link":622,"where_syntology_ran_a_sample":77,"not_listed_spam_title":0,"listed":3012,"listed_where_code_ran":77,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":64,"every_run_a_failure_of_syntologys_instrument":13,"listed_with_a_run_with_no_instrument_failure":64,"listed_every_run_a_failure_of_syntologys_instrument":13,"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"},"first_page":"/task/automatic-speech-recognition","prev":"/task/automatic-speech-recognition/papers/3","next":"/task/automatic-speech-recognition/papers/5","papers":[{"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/towards-voice-reconstruction-from-eeg-during","slug":"towards-voice-reconstruction-from-eeg-during","title":"Towards Voice Reconstruction from EEG during Imagined Speech","date":"2023-01-02","arxiv_id":"2301.07173","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-voice-reconstruction-from-eeg-during#ran","syntology_url":"https://syntology.ai/paper/2301.07173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.07173"}},"official":{"repos":["youngeun1209/neurotalk"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skit-s2i-an-indian-accented-speech-to-intent","slug":"skit-s2i-an-indian-accented-speech-to-intent","title":"Skit-S2I: An Indian Accented Speech to Intent dataset","date":"2022-12-26","arxiv_id":"2212.13015","repositories_listed":1,"syntology":null},{"url":"/paper/nusacrowd-open-source-initiative-for","slug":"nusacrowd-open-source-initiative-for","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","date":"2022-12-19","arxiv_id":"2212.09648","repositories_listed":1,"syntology":null},{"url":"/paper/blaser-a-text-free-speech-to-speech","slug":"blaser-a-text-free-speech-to-speech","title":"BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric","date":"2022-12-16","arxiv_id":"2212.08486","repositories_listed":1,"syntology":null},{"url":"/paper/effectiveness-of-text-acoustic-and-lattice","slug":"effectiveness-of-text-acoustic-and-lattice","title":"Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks","date":"2022-12-16","arxiv_id":"2212.08489","repositories_listed":1,"syntology":null},{"url":"/paper/baspro-a-balanced-script-producer-for-speech","slug":"baspro-a-balanced-script-producer-for-speech","title":"BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithm","date":"2022-12-11","arxiv_id":"2301.04120","repositories_listed":1,"syntology":null},{"url":"/paper/softctc-unicode-x2013-semi-supervised","slug":"softctc-unicode-x2013-semi-supervised","title":"SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels","date":"2022-12-05","arxiv_id":"2212.02135","repositories_listed":1,"syntology":null},{"url":"/paper/softcorrect-error-correction-with-soft","slug":"softcorrect-error-correction-with-soft","title":"SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition","date":"2022-12-02","arxiv_id":"2212.01039","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/softcorrect-error-correction-with-soft#ran","syntology_url":"https://syntology.ai/paper/2212.01039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.01039"}},"official":{"repos":["microsoft/NeuralSpeech"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/euro-espnet-unsupervised-asr-open-source","slug":"euro-espnet-unsupervised-asr-open-source","title":"EURO: ESPnet Unsupervised ASR Open-source Toolkit","date":"2022-11-30","arxiv_id":"2211.17196","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/euro-espnet-unsupervised-asr-open-source#ran","syntology_url":"https://syntology.ai/paper/2211.17196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.17196"}},"official":{"repos":["espnet/espnet"],"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":["official"]}}},{"url":"/paper/mmspeech-multi-modal-multi-task-encoder","slug":"mmspeech-multi-modal-multi-task-encoder","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition","date":"2022-11-29","arxiv_id":"2212.00500","repositories_listed":1,"syntology":null},{"url":"/paper/whose-emotion-matters-speaker-detection","slug":"whose-emotion-matters-speaker-detection","title":"Whose Emotion Matters? Speaking Activity Localisation without Prior Knowledge","date":"2022-11-23","arxiv_id":"2211.15377","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-unified-conformer-structure-from","slug":"towards-a-unified-conformer-structure-from","title":"Towards A Unified Conformer Structure: from ASR to ASV Task","date":"2022-11-14","arxiv_id":"2211.07201","repositories_listed":1,"syntology":null},{"url":"/paper/the-far-side-of-failure-investigating-the","slug":"the-far-side-of-failure-investigating-the","title":"The Far Side of Failure: Investigating the Impact of Speech Recognition Errors on Subsequent Dementia Classification","date":"2022-11-11","arxiv_id":"2211.07430","repositories_listed":1,"syntology":null},{"url":"/paper/robust-unstructured-knowledge-access-in","slug":"robust-unstructured-knowledge-access-in","title":"Robust Unstructured Knowledge Access in Conversational Dialogue with ASR Errors","date":"2022-11-08","arxiv_id":"2211.03990","repositories_listed":1,"syntology":null},{"url":"/paper/towards-improved-room-impulse-response","slug":"towards-improved-room-impulse-response","title":"Towards Improved Room Impulse Response Estimation for Speech Recognition","date":"2022-11-08","arxiv_id":"2211.04473","repositories_listed":1,"syntology":null},{"url":"/paper/data2vec-aqc-search-for-the-right-teaching","slug":"data2vec-aqc-search-for-the-right-teaching","title":"data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup","date":"2022-11-02","arxiv_id":"2211.01246","repositories_listed":1,"syntology":null},{"url":"/paper/intermpl-momentum-pseudo-labeling-with","slug":"intermpl-momentum-pseudo-labeling-with","title":"InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss","date":"2022-11-02","arxiv_id":"2211.00795","repositories_listed":1,"syntology":null},{"url":"/paper/losses-can-be-blessings-routing-self","slug":"losses-can-be-blessings-routing-self","title":"Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing","date":"2022-11-02","arxiv_id":"2211.01522","repositories_listed":1,"syntology":null},{"url":"/paper/blank-collapse-compressing-ctc-emission-for","slug":"blank-collapse-compressing-ctc-emission-for","title":"Blank Collapse: Compressing CTC emission for the faster decoding","date":"2022-10-31","arxiv_id":"2210.17017","repositories_listed":1,"syntology":null},{"url":"/paper/delay-penalized-transducer-for-low-latency","slug":"delay-penalized-transducer-for-low-latency","title":"Delay-penalized transducer for low-latency streaming ASR","date":"2022-10-31","arxiv_id":"2211.00490","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-multi-codebook-vector-quantization","slug":"predicting-multi-codebook-vector-quantization","title":"Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation","date":"2022-10-31","arxiv_id":"2211.00508","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-severity-assessment-of-dysarthric","slug":"automatic-severity-assessment-of-dysarthric","title":"Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with Multi-task Learning","date":"2022-10-27","arxiv_id":"2210.15387","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-pseudo-forced-alignment-by-acoustic","slug":"iterative-pseudo-forced-alignment-by-acoustic","title":"Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation","date":"2022-10-27","arxiv_id":"2210.15226","repositories_listed":1,"syntology":null},{"url":"/paper/on-out-of-distribution-detection-for-audio","slug":"on-out-of-distribution-detection-for-audio","title":"On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors","date":"2022-10-27","arxiv_id":"2210.15283","repositories_listed":1,"syntology":null},{"url":"/paper/robust-data2vec-noise-robust-speech","slug":"robust-data2vec-noise-robust-speech","title":"Robust Data2vec: Noise-robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning","date":"2022-10-27","arxiv_id":"2210.15324","repositories_listed":1,"syntology":null},{"url":"/paper/monotonic-segmental-attention-for-automatic","slug":"monotonic-segmental-attention-for-automatic","title":"Monotonic segmental attention for automatic speech recognition","date":"2022-10-26","arxiv_id":"2210.14742","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-language-confusion-for-code","slug":"reducing-language-confusion-for-code","title":"Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization","date":"2022-10-26","arxiv_id":"2210.14567","repositories_listed":1,"syntology":null},{"url":"/paper/there-is-more-than-one-kind-of-robustness","slug":"there-is-more-than-one-kind-of-robustness","title":"There is more than one kind of robustness: Fooling Whisper with adversarial examples","date":"2022-10-26","arxiv_id":"2210.17316","repositories_listed":1,"syntology":null},{"url":"/paper/brouhaha-multi-task-training-for-voice","slug":"brouhaha-multi-task-training-for-voice","title":"Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation","date":"2022-10-24","arxiv_id":"2210.13248","repositories_listed":1,"syntology":null},{"url":"/paper/does-joint-training-really-help-cascaded","slug":"does-joint-training-really-help-cascaded","title":"Does Joint Training Really Help Cascaded Speech Translation?","date":"2022-10-24","arxiv_id":"2210.13700","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-cross-modal-alignment-enables-zero","slug":"discrete-cross-modal-alignment-enables-zero","title":"Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation","date":"2022-10-18","arxiv_id":"2210.09556","repositories_listed":1,"syntology":null},{"url":"/paper/towards-relation-extraction-from-speech","slug":"towards-relation-extraction-from-speech","title":"Towards Relation Extraction From Speech","date":"2022-10-17","arxiv_id":"2210.08759","repositories_listed":1,"syntology":null},{"url":"/paper/bringing-nurc-sp-to-digital-life-the-role-of","slug":"bringing-nurc-sp-to-digital-life-the-role-of","title":"Bringing NURC/SP to Digital Life: the Role of Open-source Automatic Speech Recognition Models","date":"2022-10-14","arxiv_id":"2210.07852","repositories_listed":1,"syntology":null},{"url":"/paper/a-context-aware-knowledge-transferring","slug":"a-context-aware-knowledge-transferring","title":"A context-aware knowledge transferring strategy for CTC-based ASR","date":"2022-10-12","arxiv_id":"2210.06244","repositories_listed":1,"syntology":null},{"url":"/paper/can-we-use-common-voice-to-train-a-multi","slug":"can-we-use-common-voice-to-train-a-multi","title":"Can we use Common Voice to train a Multi-Speaker TTS system?","date":"2022-10-12","arxiv_id":"2210.06370","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-we-use-common-voice-to-train-a-multi#ran","syntology_url":"https://syntology.ai/paper/2210.06370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06370"}},"official":null}},{"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":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 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":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/joeys2t-minimalistic-speech-to-text-modeling","slug":"joeys2t-minimalistic-speech-to-text-modeling","title":"JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT","date":"2022-10-05","arxiv_id":"2210.02545","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":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/joeys2t-minimalistic-speech-to-text-modeling#ran","syntology_url":"https://syntology.ai/paper/2210.02545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02545"}},"official":{"repos":["may-/joeys2t"],"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/e-branchformer-branchformer-with-enhanced","slug":"e-branchformer-branchformer-with-enhanced","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","date":"2022-09-30","arxiv_id":"2210.00077","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-impact-of-speech-recognition-errors-in","slug":"on-the-impact-of-speech-recognition-errors-in","title":"On the Impact of Speech Recognition Errors in Passage Retrieval for Spoken Question Answering","date":"2022-09-26","arxiv_id":"2209.12944","repositories_listed":1,"syntology":null},{"url":"/paper/watch-what-you-pretrain-for-targeted","slug":"watch-what-you-pretrain-for-targeted","title":"Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models","date":"2022-09-17","arxiv_id":"2209.13523","repositories_listed":1,"syntology":null},{"url":"/paper/an-automatic-speech-recognition-system-for","slug":"an-automatic-speech-recognition-system-for","title":"An Automatic Speech Recognition System for Bengali Language based on Wav2Vec2 and Transfer Learning","date":"2022-09-16","arxiv_id":"2209.08119","repositories_listed":1,"syntology":null},{"url":"/paper/non-autoregressive-error-correction-for-ctc","slug":"non-autoregressive-error-correction-for-ctc","title":"Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM","date":"2022-09-08","arxiv_id":"2209.04062","repositories_listed":1,"syntology":null},{"url":"/paper/mlphon-a-multifunctional-grapheme-phoneme","slug":"mlphon-a-multifunctional-grapheme-phoneme","title":"Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers","date":"2022-09-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semantically-meaningful-metrics-for-norwegian","slug":"semantically-meaningful-metrics-for-norwegian","title":"Semantically Meaningful Metrics for Norwegian ASR Systems","date":"2022-09-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-sparse-conformer-for-speech-recognition","slug":"deep-sparse-conformer-for-speech-recognition","title":"Deep Sparse Conformer for Speech Recognition","date":"2022-09-01","arxiv_id":"2209.00260","repositories_listed":1,"syntology":null},{"url":"/paper/indicsuperb-a-speech-processing-universal","slug":"indicsuperb-a-speech-processing-universal","title":"IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages","date":"2022-08-24","arxiv_id":"2208.11761","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/indicsuperb-a-speech-processing-universal#ran","syntology_url":"https://syntology.ai/paper/2208.11761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.11761"}},"official":{"repos":["AI4Bharat/indicSUPERB"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-robustness-of-end-to-end-neural","slug":"analyzing-robustness-of-end-to-end-neural","title":"Analyzing Robustness of End-to-End Neural Models for Automatic Speech Recognition","date":"2022-08-17","arxiv_id":"2208.08509","repositories_listed":1,"syntology":null},{"url":"/paper/comparison-and-analysis-of-new-curriculum","slug":"comparison-and-analysis-of-new-curriculum","title":"Comparison and Analysis of New Curriculum Criteria for End-to-End ASR","date":"2022-08-10","arxiv_id":"2208.05782","repositories_listed":1,"syntology":null},{"url":"/paper/asr-error-correction-with-constrained","slug":"asr-error-correction-with-constrained","title":"ASR Error Correction with Constrained Decoding on Operation Prediction","date":"2022-08-09","arxiv_id":"2208.04641","repositories_listed":1,"syntology":null},{"url":"/paper/thai-wav2vec2-0-with-commonvoice-v8","slug":"thai-wav2vec2-0-with-commonvoice-v8","title":"Thai Wav2Vec2.0 with CommonVoice V8","date":"2022-08-09","arxiv_id":"2208.04799","repositories_listed":1,"syntology":null},{"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/domain-specific-wav2vec-2-0-fine-tuning-for","slug":"domain-specific-wav2vec-2-0-fine-tuning-for","title":"Domain Specific Wav2vec 2.0 Fine-tuning For The SE&R 2022 Challenge","date":"2022-07-29","arxiv_id":"2207.14418","repositories_listed":1,"syntology":null},{"url":"/paper/towards-transfer-learning-of-wav2vec-2-0-for","slug":"towards-transfer-learning-of-wav2vec-2-0-for","title":"Transfer Learning of wav2vec 2.0 for Automatic Lyric Transcription","date":"2022-07-20","arxiv_id":"2207.09747","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-transfer-learning-of-wav2vec-2-0-for#ran","syntology_url":"https://syntology.ai/paper/2207.09747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09747"}},"official":{"repos":["guxm2021/alt_speechbrain"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/when-is-tts-augmentation-through-a-pivot","slug":"when-is-tts-augmentation-through-a-pivot","title":"When Is TTS Augmentation Through a Pivot Language Useful?","date":"2022-07-20","arxiv_id":"2207.09889","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/mm-alt-a-multimodal-automatic-lyric","slug":"mm-alt-a-multimodal-automatic-lyric","title":"MM-ALT: A Multimodal Automatic Lyric Transcription System","date":"2022-07-13","arxiv_id":"2207.06127","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-anonymization-with-phonetic","slug":"speaker-anonymization-with-phonetic","title":"Speaker Anonymization with Phonetic Intermediate Representations","date":"2022-07-11","arxiv_id":"2207.04834","repositories_listed":1,"syntology":null},{"url":"/paper/behancepr-a-punctuation-restoration-dataset","slug":"behancepr-a-punctuation-restoration-dataset","title":"BehancePR: A Punctuation Restoration Dataset for Livestreaming Video Transcript","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stop-a-dataset-for-spoken-task-oriented","slug":"stop-a-dataset-for-spoken-task-oriented","title":"STOP: A dataset for Spoken Task Oriented Semantic Parsing","date":"2022-06-29","arxiv_id":"2207.10643","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-a-pretrained-language-model-to-a","slug":"distilling-a-pretrained-language-model-to-a","title":"Distilling a Pretrained Language Model to a Multilingual ASR Model","date":"2022-06-25","arxiv_id":"2206.12638","repositories_listed":1,"syntology":null},{"url":"/paper/a-systematic-comparison-of-phonetic-aware","slug":"a-systematic-comparison-of-phonetic-aware","title":"A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement","date":"2022-06-22","arxiv_id":"2206.11000","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-cross-domain-speech-recognition-with","slug":"boosting-cross-domain-speech-recognition-with","title":"Boosting Cross-Domain Speech Recognition with Self-Supervision","date":"2022-06-20","arxiv_id":"2206.09783","repositories_listed":1,"syntology":null},{"url":"/paper/avatar-unconstrained-audiovisual-speech","slug":"avatar-unconstrained-audiovisual-speech","title":"AVATAR: Unconstrained Audiovisual Speech Recognition","date":"2022-06-15","arxiv_id":"2206.07684","repositories_listed":1,"syntology":null},{"url":"/paper/lae-language-aware-encoder-for-monolingual","slug":"lae-language-aware-encoder-for-monolingual","title":"LAE: Language-Aware Encoder for Monolingual and Multilingual ASR","date":"2022-06-05","arxiv_id":"2206.02093","repositories_listed":1,"syntology":null},{"url":"/paper/ssr7000-a-synchronized-corpus-of-ultrasound","slug":"ssr7000-a-synchronized-corpus-of-ultrasound","title":"SSR7000: A Synchronized Corpus of Ultrasound Tongue Imaging for End-to-End Silent Speech Recognition","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fleurs-few-shot-learning-evaluation-of","slug":"fleurs-few-shot-learning-evaluation-of","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","date":"2022-05-25","arxiv_id":"2205.12446","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-with-image-descriptors-are","slug":"language-models-with-image-descriptors-are","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","date":"2022-05-22","arxiv_id":"2205.10747","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-with-image-descriptors-are#ran","syntology_url":"https://syntology.ai/paper/2205.10747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10747"}},"official":{"repos":["mikewangwzhl/vidil"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/who-are-we-talking-about-handling-person-2","slug":"who-are-we-talking-about-handling-person-2","title":"Who Are We Talking About? Handling Person Names in Speech Translation","date":"2022-05-13","arxiv_id":"2205.06755","repositories_listed":1,"syntology":null},{"url":"/paper/vietnamese-automatic-speech-recognition-using","slug":"vietnamese-automatic-speech-recognition-using","title":"Vietnamese Automatic Speech Recognition using Wav2vec 2.0","date":"2022-05-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-multi-aspect-multi","slug":"transformer-based-multi-aspect-multi","title":"Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment","date":"2022-05-06","arxiv_id":"2205.03432","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-recognition-in-the-wild","slug":"speaker-recognition-in-the-wild","title":"Speaker Recognition in the Wild","date":"2022-05-05","arxiv_id":"2205.02475","repositories_listed":1,"syntology":null},{"url":"/paper/wav2seq-pre-training-speech-to-text-encoder","slug":"wav2seq-pre-training-speech-to-text-encoder","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","date":"2022-05-02","arxiv_id":"2205.01086","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-speech-recognition-and-query-by","slug":"automatic-speech-recognition-and-query-by","title":"Automatic Speech Recognition and Query By Example for Creole Languages Documentation","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/how-you-say-it-matters-measuring-the-impact","slug":"how-you-say-it-matters-measuring-the-impact","title":"How You Say It Matters: Measuring the Impact of Verbal Disfluency Tags on Automated Dementia Detection","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-non-autoregressive-generation-for","slug":"a-survey-on-non-autoregressive-generation-for","title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","date":"2022-04-20","arxiv_id":"2204.09269","repositories_listed":1,"syntology":null},{"url":"/paper/hubert-ee-early-exiting-hubert-for-efficient","slug":"hubert-ee-early-exiting-hubert-for-efficient","title":"HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition","date":"2022-04-13","arxiv_id":"2204.06328","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-streaming-end-to-end-speech","slug":"large-scale-streaming-end-to-end-speech","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","date":"2022-04-11","arxiv_id":"2204.05352","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-scale-streaming-end-to-end-speech#ran","syntology_url":"https://syntology.ai/paper/2204.05352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05352"}},"official":null}},{"url":"/paper/unsupervised-uncertainty-measures-of","slug":"unsupervised-uncertainty-measures-of","title":"Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction","date":"2022-04-08","arxiv_id":"2204.04288","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unsupervised-uncertainty-measures-of#ran","syntology_url":"https://syntology.ai/paper/2204.04288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.04288"}},"official":{"repos":["claritychallenge/clarity"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/combining-spectral-and-self-supervised","slug":"combining-spectral-and-self-supervised","title":"Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation","date":"2022-04-05","arxiv_id":"2204.02470","repositories_listed":1,"syntology":null},{"url":"/paper/towards-end-to-end-unsupervised-speech","slug":"towards-end-to-end-unsupervised-speech","title":"Towards End-to-end Unsupervised Speech Recognition","date":"2022-04-05","arxiv_id":"2204.02492","repositories_listed":1,"syntology":null},{"url":"/paper/primock57-a-dataset-of-primary-care-mock","slug":"primock57-a-dataset-of-primary-care-mock","title":"PriMock57: A Dataset Of Primary Care Mock Consultations","date":"2022-04-01","arxiv_id":"2204.00333","repositories_listed":1,"syntology":null},{"url":"/paper/a-hybrid-continuity-loss-to-reduce-over","slug":"a-hybrid-continuity-loss-to-reduce-over","title":"A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction","date":"2022-03-31","arxiv_id":"2203.16843","repositories_listed":1,"syntology":null},{"url":"/paper/indic-punct-an-automatic-punctuation","slug":"indic-punct-an-automatic-punctuation","title":"indic-punct: An automatic punctuation restoration and inverse text normalization framework for Indic languages","date":"2022-03-31","arxiv_id":"2203.16825","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-transformer-decoder-for-end-to","slug":"pre-training-transformer-decoder-for-end-to","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","date":"2022-03-31","arxiv_id":"2203.17113","repositories_listed":1,"syntology":null},{"url":"/paper/streaming-speaker-attributed-asr-with-token","slug":"streaming-speaker-attributed-asr-with-token","title":"Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings","date":"2022-03-30","arxiv_id":"2203.16685","repositories_listed":1,"syntology":null},{"url":"/paper/using-adapters-to-overcome-catastrophic","slug":"using-adapters-to-overcome-catastrophic","title":"Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition","date":"2022-03-30","arxiv_id":"2203.16082","repositories_listed":1,"syntology":null},{"url":"/paper/4-bit-conformer-with-native-quantization","slug":"4-bit-conformer-with-native-quantization","title":"4-bit Conformer with Native Quantization Aware Training for Speech Recognition","date":"2022-03-29","arxiv_id":"2203.15952","repositories_listed":1,"syntology":null},{"url":"/paper/a-single-speaker-is-almost-all-you-need-for","slug":"a-single-speaker-is-almost-all-you-need-for","title":"ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion","date":"2022-03-29","arxiv_id":"2204.00618","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-of-eeg-frequency-bands-for","slug":"analysis-of-eeg-frequency-bands-for","title":"Analysis of EEG frequency bands for Envisioned Speech Recognition","date":"2022-03-29","arxiv_id":"2203.15250","repositories_listed":1,"syntology":null},{"url":"/paper/earnings-22-a-practical-benchmark-for-accents","slug":"earnings-22-a-practical-benchmark-for-accents","title":"Earnings-22: A Practical Benchmark for Accents in the Wild","date":"2022-03-29","arxiv_id":"2203.15591","repositories_listed":1,"syntology":null},{"url":"/paper/integrate-lattice-free-mmi-into-end-to-end","slug":"integrate-lattice-free-mmi-into-end-to-end","title":"Integrating Lattice-Free MMI into End-to-End Speech Recognition","date":"2022-03-29","arxiv_id":"2203.15614","repositories_listed":1,"syntology":null},{"url":"/paper/lighthubert-lightweight-and-configurable","slug":"lighthubert-lightweight-and-configurable","title":"LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT","date":"2022-03-29","arxiv_id":"2203.15610","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/lighthubert-lightweight-and-configurable#ran","syntology_url":"https://syntology.ai/paper/2203.15610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15610"}},"official":{"repos":["mechanicalsea/lighthubert"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/shifted-chunk-encoder-for-transformer-based","slug":"shifted-chunk-encoder-for-transformer-based","title":"Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASR","date":"2022-03-29","arxiv_id":"2203.15206","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-text-to-speech-synthesis-by","slug":"unsupervised-text-to-speech-synthesis-by","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","date":"2022-03-29","arxiv_id":"2203.15796","repositories_listed":1,"syntology":null},{"url":"/paper/cmgan-conformer-based-metric-gan-for-speech","slug":"cmgan-conformer-based-metric-gan-for-speech","title":"CMGAN: Conformer-based Metric GAN for Speech Enhancement","date":"2022-03-28","arxiv_id":"2203.15149","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cmgan-conformer-based-metric-gan-for-speech#ran","syntology_url":"https://syntology.ai/paper/2203.15149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15149"}},"official":{"repos":["ruizhecao96/cmgan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/finnish-parliament-asr-corpus-analysis","slug":"finnish-parliament-asr-corpus-analysis","title":"Finnish Parliament ASR corpus - Analysis, benchmarks and statistics","date":"2022-03-28","arxiv_id":"2203.14876","repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-for-speech-emotion-recognition-in","slug":"a-dataset-for-speech-emotion-recognition-in","title":"A Dataset for Speech Emotion Recognition in Greek Theatrical Plays","date":"2022-03-27","arxiv_id":"2203.15568","repositories_listed":1,"syntology":null},{"url":"/paper/towards-privacy-preserving-speech","slug":"towards-privacy-preserving-speech","title":"A Speech Representation Anonymization Framework via Selective Noise Perturbation","date":"2022-03-26","arxiv_id":"2203.14171","repositories_listed":1,"syntology":null}],"record_sha256":"12f32e43db96121ba68afa56aa6e950ae38ca450b03eb5f9204fff99640040d5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}