{"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-2/papers/4","list_of":"/task/automatic-speech-recognition-2","task":"Automatic Speech Recognition","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":32,"rows_per_page":100,"rows":[301,400],"of":3174,"counts":{"archive_papers_tagged":3174,"with_a_code_link":677,"where_syntology_ran_a_sample":79,"not_listed_spam_title":0,"listed":3174,"listed_where_code_ran":79,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":62,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":62,"listed_every_run_a_failure_of_syntologys_instrument":17,"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-2","prev":"/task/automatic-speech-recognition-2/papers/3","next":"/task/automatic-speech-recognition-2/papers/5","papers":[{"url":"/paper/end-to-end-open-vocabulary-keyword-search-1","slug":"end-to-end-open-vocabulary-keyword-search-1","title":"End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations","date":"2023-08-15","arxiv_id":"2308.08027","repositories_listed":1,"syntology":null},{"url":"/paper/improving-audio-visual-speech-recognition-by","slug":"improving-audio-visual-speech-recognition-by","title":"Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder","date":"2023-08-14","arxiv_id":"2308.08488","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-emotion-recognition-with-speech","slug":"integrating-emotion-recognition-with-speech","title":"Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for Conversations","date":"2023-08-14","arxiv_id":"2308.07145","repositories_listed":1,"syntology":null},{"url":"/paper/omnidatacomposer-a-unified-data-structure-for","slug":"omnidatacomposer-a-unified-data-structure-for","title":"OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation","date":"2023-08-08","arxiv_id":"2308.04126","repositories_listed":1,"syntology":null},{"url":"/paper/iroyinspeech-a-multi-purpose-yoruba-speech","slug":"iroyinspeech-a-multi-purpose-yoruba-speech","title":"ÌròyìnSpeech: A multi-purpose Yorùbá Speech Corpus","date":"2023-07-29","arxiv_id":"2307.16071","repositories_listed":1,"syntology":null},{"url":"/paper/a-model-for-every-user-and-budget-label-free","slug":"a-model-for-every-user-and-budget-label-free","title":"A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization","date":"2023-07-24","arxiv_id":"2307.12659","repositories_listed":1,"syntology":null},{"url":"/paper/adaptation-of-whisper-models-to-child-speech","slug":"adaptation-of-whisper-models-to-child-speech","title":"Adaptation of Whisper models to child speech recognition","date":"2023-07-24","arxiv_id":"2307.13008","repositories_listed":1,"syntology":null},{"url":"/paper/code-switched-urdu-asr-for-noisy-telephonic","slug":"code-switched-urdu-asr-for-noisy-telephonic","title":"Code-Switched Urdu ASR for Noisy Telephonic Environment using Data Centric Approach with Hybrid HMM and CNN-TDNN","date":"2023-07-24","arxiv_id":"2307.12759","repositories_listed":1,"syntology":null},{"url":"/paper/a-change-of-heart-improving-speech-emotion","slug":"a-change-of-heart-improving-speech-emotion","title":"A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality Conversion","date":"2023-07-21","arxiv_id":"2307.11584","repositories_listed":1,"syntology":null},{"url":"/paper/topic-identification-for-spontaneous-speech","slug":"topic-identification-for-spontaneous-speech","title":"Topic Identification For Spontaneous Speech: Enriching Audio Features With Embedded Linguistic Information","date":"2023-07-21","arxiv_id":"2307.11450","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-dive-into-the-disparity-of-word-error","slug":"a-deep-dive-into-the-disparity-of-word-error","title":"A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos","date":"2023-07-20","arxiv_id":"2307.10587","repositories_listed":1,"syntology":null},{"url":"/paper/oxfordvgg-submission-to-the-ego4d-av","slug":"oxfordvgg-submission-to-the-ego4d-av","title":"OxfordVGG Submission to the EGO4D AV Transcription Challenge","date":"2023-07-18","arxiv_id":"2307.09006","repositories_listed":1,"syntology":null},{"url":"/paper/writer-adaptation-for-offline-text","slug":"writer-adaptation-for-offline-text","title":"Writer adaptation for offline text recognition: An exploration of neural network-based methods","date":"2023-07-11","arxiv_id":"2307.15071","repositories_listed":1,"syntology":null},{"url":"/paper/a-reference-less-quality-metric-for-automatic","slug":"a-reference-less-quality-metric-for-automatic","title":"A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-Supervision","date":"2023-06-21","arxiv_id":"2306.13114","repositories_listed":1,"syntology":null},{"url":"/paper/norefer-a-referenceless-quality-metric-for","slug":"norefer-a-referenceless-quality-metric-for","title":"NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive Learning","date":"2023-06-21","arxiv_id":"2306.12577","repositories_listed":1,"syntology":null},{"url":"/paper/rehearsal-free-online-continual-learning-for","slug":"rehearsal-free-online-continual-learning-for","title":"Rehearsal-Free Online Continual Learning for Automatic Speech Recognition","date":"2023-06-19","arxiv_id":"2306.10860","repositories_listed":1,"syntology":null},{"url":"/paper/pushing-the-limits-of-unsupervised-unit","slug":"pushing-the-limits-of-unsupervised-unit","title":"Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation","date":"2023-06-15","arxiv_id":"2306.08920","repositories_listed":1,"syntology":null},{"url":"/paper/towards-training-bilingual-and-code-switched","slug":"towards-training-bilingual-and-code-switched","title":"Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer","date":"2023-06-14","arxiv_id":"2306.08753","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-training-for-low-resource","slug":"adversarial-training-for-low-resource","title":"Adversarial Training For Low-Resource Disfluency Correction","date":"2023-06-10","arxiv_id":"2306.06384","repositories_listed":1,"syntology":null},{"url":"/paper/a-theory-of-unsupervised-speech-recognition","slug":"a-theory-of-unsupervised-speech-recognition","title":"A Theory of Unsupervised Speech Recognition","date":"2023-06-09","arxiv_id":"2306.07926","repositories_listed":1,"syntology":null},{"url":"/paper/arabic-dysarthric-speech-recognition-using","slug":"arabic-dysarthric-speech-recognition-using","title":"Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based Augmentation","date":"2023-06-07","arxiv_id":"2306.04368","repositories_listed":1,"syntology":null},{"url":"/paper/spellmapper-a-non-autoregressive-neural","slug":"spellmapper-a-non-autoregressive-neural","title":"SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings","date":"2023-06-04","arxiv_id":"2306.02317","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-pretrained-asr-models-to-low","slug":"adapting-pretrained-asr-models-to-low","title":"Advancing African-Accented Speech Recognition: Epistemic Uncertainty-Driven Data Selection for Generalizable ASR Models","date":"2023-06-03","arxiv_id":"2306.02105","repositories_listed":1,"syntology":null},{"url":"/paper/sgem-test-time-adaptation-for-automatic","slug":"sgem-test-time-adaptation-for-automatic","title":"SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization","date":"2023-06-03","arxiv_id":"2306.01981","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/sgem-test-time-adaptation-for-automatic#ran","syntology_url":"https://syntology.ai/paper/2306.01981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01981"}},"official":{"repos":["drumpt/sgem"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/can-contextual-biasing-remain-effective-with","slug":"can-contextual-biasing-remain-effective-with","title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","date":"2023-06-02","arxiv_id":"2306.01942","repositories_listed":1,"syntology":null},{"url":"/paper/explainability-of-speech-recognition","slug":"explainability-of-speech-recognition","title":"Explainability of Speech Recognition Transformers via Gradient-based Attention Visualization","date":"2023-06-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improved-deepfake-detection-using-whisper","slug":"improved-deepfake-detection-using-whisper","title":"Improved DeepFake Detection Using Whisper Features","date":"2023-06-02","arxiv_id":"2306.01428","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improved-deepfake-detection-using-whisper#ran","syntology_url":"https://syntology.ai/paper/2306.01428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01428"}},"official":{"repos":["piotrkawa/deepfake-whisper-features"],"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/slothspeech-denial-of-service-attack-against","slug":"slothspeech-denial-of-service-attack-against","title":"SlothSpeech: Denial-of-service Attack Against Speech Recognition Models","date":"2023-06-01","arxiv_id":"2306.00794","repositories_listed":1,"syntology":null},{"url":"/paper/graph-neural-networks-for-contextual-asr-with","slug":"graph-neural-networks-for-contextual-asr-with","title":"Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator","date":"2023-05-30","arxiv_id":"2305.18824","repositories_listed":1,"syntology":null},{"url":"/paper/commonaccent-exploring-large-acoustic","slug":"commonaccent-exploring-large-acoustic","title":"CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice","date":"2023-05-29","arxiv_id":"2305.18283","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-characteristics-of-the-output","slug":"leveraging-characteristics-of-the-output","title":"DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution","date":"2023-05-26","arxiv_id":"2305.17000","repositories_listed":1,"syntology":null},{"url":"/paper/copyne-better-contextual-asr-by-copying-named","slug":"copyne-better-contextual-asr-by-copying-named","title":"CopyNE: Better Contextual ASR by Copying Named Entities","date":"2023-05-22","arxiv_id":"2305.12839","repositories_listed":1,"syntology":null},{"url":"/paper/bat-boundary-aware-transducer-for-memory","slug":"bat-boundary-aware-transducer-for-memory","title":"BAT: Boundary aware transducer for memory-efficient and low-latency ASR","date":"2023-05-19","arxiv_id":"2305.11571","repositories_listed":1,"syntology":null},{"url":"/paper/blank-regularized-ctc-for-frame-skipping-in","slug":"blank-regularized-ctc-for-frame-skipping-in","title":"Blank-regularized CTC for Frame Skipping in Neural Transducer","date":"2023-05-19","arxiv_id":"2305.11558","repositories_listed":1,"syntology":null},{"url":"/paper/making-more-of-little-data-improving-low","slug":"making-more-of-little-data-improving-low","title":"Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation","date":"2023-05-18","arxiv_id":"2305.10951","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/making-more-of-little-data-improving-low#ran","syntology_url":"https://syntology.ai/paper/2305.10951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10951"}},"official":{"repos":["bartelds/asr-augmentation"],"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/cross-modal-global-interaction-and-local","slug":"cross-modal-global-interaction-and-local","title":"Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition","date":"2023-05-16","arxiv_id":"2305.09212","repositories_listed":1,"syntology":null},{"url":"/paper/back-translation-for-speech-to-text","slug":"back-translation-for-speech-to-text","title":"Back Translation for Speech-to-text Translation Without Transcripts","date":"2023-05-15","arxiv_id":"2305.08709","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-variants-of-wav2vec-2-0-on","slug":"evaluating-variants-of-wav2vec-2-0-on","title":"Evaluating Variants of wav2vec 2.0 on Affective Vocal Burst Tasks","date":"2023-05-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-better-domain-adaptation-for-self","slug":"towards-better-domain-adaptation-for-self","title":"Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASR","date":"2023-04-28","arxiv_id":"2305.00115","repositories_listed":1,"syntology":null},{"url":"/paper/olisia-a-cascade-system-for-spoken-dialogue","slug":"olisia-a-cascade-system-for-spoken-dialogue","title":"OLISIA: a Cascade System for Spoken Dialogue State Tracking","date":"2023-04-20","arxiv_id":"2304.11073","repositories_listed":1,"syntology":null},{"url":"/paper/cb-conformer-contextual-biasing-conformer-for","slug":"cb-conformer-contextual-biasing-conformer-for","title":"CB-Conformer: Contextual biasing Conformer for biased word recognition","date":"2023-04-19","arxiv_id":"2304.09607","repositories_listed":1,"syntology":null},{"url":"/paper/political-corpus-creation-through-automatic","slug":"political-corpus-creation-through-automatic","title":"Political corpus creation through automatic speech recognition on EU debates","date":"2023-04-17","arxiv_id":"2304.08137","repositories_listed":1,"syntology":null},{"url":"/paper/cascading-and-direct-approaches-to","slug":"cascading-and-direct-approaches-to","title":"Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences","date":"2023-03-15","arxiv_id":"2303.08809","repositories_listed":1,"syntology":null},{"url":"/paper/hybridformer-improving-squeezeformer-with","slug":"hybridformer-improving-squeezeformer-with","title":"HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanism","date":"2023-03-15","arxiv_id":"2303.08636","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-strategies-for-faster-inference","slug":"fine-tuning-strategies-for-faster-inference","title":"Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study","date":"2023-03-12","arxiv_id":"2303.06740","repositories_listed":1,"syntology":null},{"url":"/paper/stabilizing-transformer-training-by","slug":"stabilizing-transformer-training-by","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","date":"2023-03-11","arxiv_id":"2303.06296","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stabilizing-transformer-training-by#ran","syntology_url":"https://syntology.ai/paper/2303.06296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06296"}},"official":{"repos":["apple/ml-sigma-reparam"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transcription-free-filler-word-detection-with","slug":"transcription-free-filler-word-detection-with","title":"Transcription free filler word detection with Neural semi-CRFs","date":"2023-03-11","arxiv_id":"2303.06475","repositories_listed":1,"syntology":null},{"url":"/paper/language-universal-adapter-learning-with","slug":"language-universal-adapter-learning-with","title":"Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech Recognition","date":"2023-02-28","arxiv_id":"2303.01249","repositories_listed":1,"syntology":null},{"url":"/paper/low-latency-transformers-for-speech","slug":"low-latency-transformers-for-speech","title":"A low latency attention module for streaming self-supervised speech representation learning","date":"2023-02-27","arxiv_id":"2302.13451","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-speech-recognition-for-language","slug":"multimodal-speech-recognition-for-language","title":"Multimodal Speech Recognition for Language-Guided Embodied Agents","date":"2023-02-27","arxiv_id":"2302.14030","repositories_listed":1,"syntology":null},{"url":"/paper/text-only-domain-adaptation-for-end-to-end","slug":"text-only-domain-adaptation-for-end-to-end","title":"Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator","date":"2023-02-27","arxiv_id":"2302.14036","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-ensemble-architecture-for","slug":"efficient-ensemble-architecture-for","title":"Efficient Ensemble for Multimodal Punctuation Restoration using Time-Delay Neural Network","date":"2023-02-26","arxiv_id":"2302.13376","repositories_listed":1,"syntology":null},{"url":"/paper/improving-massively-multilingual-asr-with","slug":"improving-massively-multilingual-asr-with","title":"Improving Massively Multilingual ASR With Auxiliary CTC Objectives","date":"2023-02-24","arxiv_id":"2302.12829","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/a-sidecar-separator-can-convert-a-single","slug":"a-sidecar-separator-can-convert-a-single","title":"A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One","date":"2023-02-20","arxiv_id":"2302.09908","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-score-based-speaker-adaptation-of","slug":"confidence-score-based-speaker-adaptation-of","title":"Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems","date":"2023-02-15","arxiv_id":"2302.07521","repositories_listed":1,"syntology":null},{"url":"/paper/asdf-a-differential-testing-framework-for","slug":"asdf-a-differential-testing-framework-for","title":"ASDF: A Differential Testing Framework for Automatic Speech Recognition Systems","date":"2023-02-11","arxiv_id":"2302.05582","repositories_listed":1,"syntology":null},{"url":"/paper/complex-dynamic-neurons-improved-spiking","slug":"complex-dynamic-neurons-improved-spiking","title":"Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech Recognition","date":"2023-02-02","arxiv_id":"2302.01194","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/complex-dynamic-neurons-improved-spiking#ran","syntology_url":"https://syntology.ai/paper/2302.01194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01194"}},"official":{"repos":["MingLunHan/CIF-PyTorch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-information-fusion-for-voice","slug":"cross-modal-information-fusion-for-voice","title":"Cross-modal information fusion for voice spoofing detection","date":"2023-02-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/syllable-subword-tokens-for-open-vocabulary","slug":"syllable-subword-tokens-for-open-vocabulary","title":"Syllable Subword Tokens for Open Vocabulary Speech Recognition in Malayalam","date":"2023-01-17","arxiv_id":"2301.06736","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/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/melhubert-a-simplified-hubert-on-mel","slug":"melhubert-a-simplified-hubert-on-mel","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","date":"2022-11-17","arxiv_id":"2211.09944","repositories_listed":1,"syntology":null},{"url":"/paper/mt4ssl-boosting-self-supervised-speech","slug":"mt4ssl-boosting-self-supervised-speech","title":"MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets","date":"2022-11-14","arxiv_id":"2211.07321","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/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/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}],"record_sha256":"13a89f5490ee174f0807677a7c6b4e490433c8261159ec34df92ba068714b14c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}