{"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/speech-recognition-1/papers/3","list_of":"/task/speech-recognition-1","task":"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":3,"pages_in_order":58,"rows_per_page":100,"rows":[201,300],"of":5715,"counts":{"archive_papers_tagged":5715,"with_a_code_link":1277,"where_syntology_ran_a_sample":162,"not_listed_spam_title":0,"listed":5715,"listed_where_code_ran":162,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":134,"every_run_a_failure_of_syntologys_instrument":28,"listed_with_a_run_with_no_instrument_failure":134,"listed_every_run_a_failure_of_syntologys_instrument":28,"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/speech-recognition-1","prev":"/task/speech-recognition-1/papers/2","next":"/task/speech-recognition-1/papers/4","papers":[{"url":"/paper/attention-based-models-for-text-dependent","slug":"attention-based-models-for-text-dependent","title":"Attention-Based Models for Text-Dependent Speaker Verification","date":"2017-10-28","arxiv_id":"1710.10470","repositories_listed":2,"syntology":null},{"url":"/paper/rotational-unit-of-memory","slug":"rotational-unit-of-memory","title":"Rotational Unit of Memory","date":"2017-10-26","arxiv_id":"1710.09537","repositories_listed":2,"syntology":null},{"url":"/paper/the-dirha-english-corpus-and-related-tasks","slug":"the-dirha-english-corpus-and-related-tasks","title":"The DIRHA-English corpus and related tasks for distant-speech recognition in domestic environments","date":"2017-10-06","arxiv_id":"1710.02560","repositories_listed":2,"syntology":null},{"url":"/paper/aishell-1-an-open-source-mandarin-speech","slug":"aishell-1-an-open-source-mandarin-speech","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","date":"2017-09-16","arxiv_id":"1709.05522","repositories_listed":2,"syntology":null},{"url":"/paper/twin-networks-matching-the-future-for","slug":"twin-networks-matching-the-future-for","title":"Twin Networks: Matching the Future for Sequence Generation","date":"2017-08-22","arxiv_id":"1708.06742","repositories_listed":2,"syntology":null},{"url":"/paper/chemception-a-deep-neural-network-with","slug":"chemception-a-deep-neural-network-with","title":"Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models","date":"2017-06-20","arxiv_id":"1706.06689","repositories_listed":2,"syntology":null},{"url":"/paper/3d-convolutional-neural-networks-for-cross","slug":"3d-convolutional-neural-networks-for-cross","title":"3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition","date":"2017-06-18","arxiv_id":"1706.05739","repositories_listed":2,"syntology":null},{"url":"/paper/online-and-linear-time-attention-by-enforcing","slug":"online-and-linear-time-attention-by-enforcing","title":"Online and Linear-Time Attention by Enforcing Monotonic Alignments","date":"2017-04-03","arxiv_id":"1704.00784","repositories_listed":2,"syntology":null},{"url":"/paper/sequence-modeling-via-segmentations","slug":"sequence-modeling-via-segmentations","title":"Sequence Modeling via Segmentations","date":"2017-02-24","arxiv_id":"1702.07463","repositories_listed":2,"syntology":null},{"url":"/paper/regularizing-neural-networks-by-penalizing","slug":"regularizing-neural-networks-by-penalizing","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","date":"2017-01-23","arxiv_id":"1701.06548","repositories_listed":2,"syntology":null},{"url":"/paper/can-active-memory-replace-attention","slug":"can-active-memory-replace-attention","title":"Can Active Memory Replace Attention?","date":"2016-10-27","arxiv_id":"1610.08613","repositories_listed":2,"syntology":null},{"url":"/paper/very-deep-convolutional-networks-for-end-to","slug":"very-deep-convolutional-networks-for-end-to","title":"Very Deep Convolutional Networks for End-to-End Speech Recognition","date":"2016-10-10","arxiv_id":"1610.03022","repositories_listed":2,"syntology":null},{"url":"/paper/qsgd-communication-efficient-sgd-via-gradient","slug":"qsgd-communication-efficient-sgd-via-gradient","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","date":"2016-10-07","arxiv_id":"1610.02132","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/qsgd-communication-efficient-sgd-via-gradient#ran","syntology_url":"https://syntology.ai/paper/1610.02132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.02132"}},"official":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/trainable-frontend-for-robust-and-far-field","slug":"trainable-frontend-for-robust-and-far-field","title":"Trainable Frontend For Robust and Far-Field Keyword Spotting","date":"2016-07-19","arxiv_id":"1607.05666","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/trainable-frontend-for-robust-and-far-field#ran","syntology_url":"https://syntology.ai/paper/1607.05666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.05666"}},"official":null}},{"url":"/paper/dsd-dense-sparse-dense-training-for-deep","slug":"dsd-dense-sparse-dense-training-for-deep","title":"DSD: Dense-Sparse-Dense Training for Deep Neural Networks","date":"2016-07-15","arxiv_id":"1607.04381","repositories_listed":2,"syntology":null},{"url":"/paper/single-channel-multi-speaker-separation-using","slug":"single-channel-multi-speaker-separation-using","title":"Single-Channel Multi-Speaker Separation using Deep Clustering","date":"2016-07-07","arxiv_id":"1607.02173","repositories_listed":2,"syntology":null},{"url":"/paper/using-filter-banks-in-convolutional-neural","slug":"using-filter-banks-in-convolutional-neural","title":"Using Filter Banks in Convolutional Neural Networks for Texture Classification","date":"2016-01-12","arxiv_id":"1601.02919","repositories_listed":2,"syntology":null},{"url":"/paper/strategies-for-training-large-vocabulary","slug":"strategies-for-training-large-vocabulary","title":"Strategies for Training Large Vocabulary Neural Language Models","date":"2015-12-15","arxiv_id":"1512.04906","repositories_listed":2,"syntology":null},{"url":"/paper/an-end-to-end-neural-network-for-polyphonic","slug":"an-end-to-end-neural-network-for-polyphonic","title":"An End-to-End Neural Network for Polyphonic Piano Music Transcription","date":"2015-08-07","arxiv_id":"1508.01774","repositories_listed":2,"syntology":null},{"url":"/paper/do-deep-nets-really-need-to-be-deep","slug":"do-deep-nets-really-need-to-be-deep","title":"Do Deep Nets Really Need to be Deep?","date":"2013-12-21","arxiv_id":"1312.6184","repositories_listed":2,"syntology":null},{"url":"/paper/connectionist-temporal-classification","slug":"connectionist-temporal-classification","title":"Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks","date":"2006-07-25","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/first-steps-towards-voice-anonymization-for","slug":"first-steps-towards-voice-anonymization-for","title":"First Steps Towards Voice Anonymization for Code-Switching Speech","date":"2025-07-02","arxiv_id":"2507.01765","repositories_listed":1,"syntology":null},{"url":"/paper/splitformer-an-improved-early-exit","slug":"splitformer-an-improved-early-exit","title":"Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices","date":"2025-06-22","arxiv_id":"2506.18035","repositories_listed":1,"syntology":null},{"url":"/paper/advances-in-small-footprint-keyword-spotting","slug":"advances-in-small-footprint-keyword-spotting","title":"Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms","date":"2025-06-12","arxiv_id":"2506.11169","repositories_listed":1,"syntology":null},{"url":"/paper/addressing-pitfalls-in-auditing-practices-of","slug":"addressing-pitfalls-in-auditing-practices-of","title":"Addressing Pitfalls in Auditing Practices of Automatic Speech Recognition Technologies: A Case Study of People with Aphasia","date":"2025-06-10","arxiv_id":"2506.08846","repositories_listed":1,"syntology":null},{"url":"/paper/structured-state-space-model-dynamics-and","slug":"structured-state-space-model-dynamics-and","title":"Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks","date":"2025-06-04","arxiv_id":"2506.06374","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-rhythm-and-voice-conversion-to","slug":"unsupervised-rhythm-and-voice-conversion-to","title":"Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech","date":"2025-06-02","arxiv_id":"2506.01618","repositories_listed":1,"syntology":null},{"url":"/paper/gigaam-efficient-self-supervised-learner-for","slug":"gigaam-efficient-self-supervised-learner-for","title":"GigaAM: Efficient Self-Supervised Learner for Speech Recognition","date":"2025-06-01","arxiv_id":"2506.01192","repositories_listed":1,"syntology":null},{"url":"/paper/what-do-self-supervised-speech-models-know-1","slug":"what-do-self-supervised-speech-models-know-1","title":"What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training","date":"2025-06-01","arxiv_id":"2506.00981","repositories_listed":1,"syntology":null},{"url":"/paper/towards-temporally-explainable-dysarthric","slug":"towards-temporally-explainable-dysarthric","title":"Towards Temporally Explainable Dysarthric Speech Clarity Assessment","date":"2025-05-31","arxiv_id":"2506.00454","repositories_listed":1,"syntology":null},{"url":"/paper/vedavani-a-benchmark-corpus-for-asr-on-vedic","slug":"vedavani-a-benchmark-corpus-for-asr-on-vedic","title":"Vedavani: A Benchmark Corpus for ASR on Vedic Sanskrit Poetry","date":"2025-05-30","arxiv_id":"2506.00145","repositories_listed":1,"syntology":null},{"url":"/paper/beavertalk-oregon-state-university-s-iwslt","slug":"beavertalk-oregon-state-university-s-iwslt","title":"BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System","date":"2025-05-29","arxiv_id":"2505.24016","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-generative-error-correction-for","slug":"exploring-generative-error-correction-for","title":"Exploring Generative Error Correction for Dysarthric Speech Recognition","date":"2025-05-26","arxiv_id":"2505.20163","repositories_listed":1,"syntology":null},{"url":"/paper/chser-a-dataset-and-case-study-on-generative","slug":"chser-a-dataset-and-case-study-on-generative","title":"CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR","date":"2025-05-24","arxiv_id":"2505.18463","repositories_listed":1,"syntology":null},{"url":"/paper/daily-omni-towards-audio-visual-reasoning","slug":"daily-omni-towards-audio-visual-reasoning","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","date":"2025-05-23","arxiv_id":"2505.17862","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/daily-omni-towards-audio-visual-reasoning#ran","syntology_url":"https://syntology.ai/paper/2505.17862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17862"}},"official":{"repos":["lliar-liar/daily-omni"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/llm-based-generative-error-correction-for","slug":"llm-based-generative-error-correction-for","title":"LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context","date":"2025-05-23","arxiv_id":"2505.17410","repositories_listed":1,"syntology":null},{"url":"/paper/speechless-speech-instruction-training","slug":"speechless-speech-instruction-training","title":"Speechless: Speech Instruction Training Without Speech for Low Resource Languages","date":"2025-05-23","arxiv_id":"2505.17417","repositories_listed":1,"syntology":null},{"url":"/paper/from-tens-of-hours-to-tens-of-thousands","slug":"from-tens-of-hours-to-tens-of-thousands","title":"From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition","date":"2025-05-22","arxiv_id":"2505.16972","repositories_listed":1,"syntology":null},{"url":"/paper/word-level-timestamp-generation-for-automatic","slug":"word-level-timestamp-generation-for-automatic","title":"Word Level Timestamp Generation for Automatic Speech Recognition and Translation","date":"2025-05-21","arxiv_id":"2505.15646","repositories_listed":1,"syntology":null},{"url":"/paper/dual-precision-quantization-for-efficient-and","slug":"dual-precision-quantization-for-efficient-and","title":"Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference","date":"2025-05-20","arxiv_id":"2505.14638","repositories_listed":1,"syntology":null},{"url":"/paper/personatab-predicting-personality-traits","slug":"personatab-predicting-personality-traits","title":"PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech Dialogs","date":"2025-05-20","arxiv_id":"2505.14356","repositories_listed":1,"syntology":null},{"url":"/paper/towards-inclusive-asr-investigating-voice","slug":"towards-inclusive-asr-investigating-voice","title":"Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages","date":"2025-05-20","arxiv_id":"2505.14874","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-from-visual-speech","slug":"transfer-learning-from-visual-speech","title":"Transfer Learning from Visual Speech Recognition to Mouthing Recognition in German Sign Language","date":"2025-05-20","arxiv_id":"2505.13784","repositories_listed":1,"syntology":null},{"url":"/paper/multi-head-temporal-latent-attention","slug":"multi-head-temporal-latent-attention","title":"Multi-head Temporal Latent Attention","date":"2025-05-19","arxiv_id":"2505.13544","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/multi-head-temporal-latent-attention#ran","syntology_url":"https://syntology.ai/paper/2505.13544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13544"}},"official":{"repos":["d-keqi/mlta"],"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/2505-10879","slug":"2505-10879","title":"Multi-Stage Speaker Diarization for Noisy Classrooms","date":"2025-05-16","arxiv_id":"2505.10879","repositories_listed":1,"syntology":null},{"url":"/paper/cogenav-versatile-audio-visual-representation","slug":"cogenav-versatile-audio-visual-representation","title":"CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization","date":"2025-05-06","arxiv_id":"2505.03186","repositories_listed":1,"syntology":null},{"url":"/paper/vita-audio-fast-interleaved-cross-modal-token","slug":"vita-audio-fast-interleaved-cross-modal-token","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","date":"2025-05-06","arxiv_id":"2505.03739","repositories_listed":1,"syntology":null},{"url":"/paper/voila-voice-language-foundation-models-for","slug":"voila-voice-language-foundation-models-for","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","date":"2025-05-05","arxiv_id":"2505.02707","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/voila-voice-language-foundation-models-for#ran","syntology_url":"https://syntology.ai/paper/2505.02707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02707"}},"official":{"repos":["maitrix-org/voila"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/transforming-faces-into-video-stories","slug":"transforming-faces-into-video-stories","title":"Transforming faces into video stories -- VideoFace2.0","date":"2025-05-04","arxiv_id":"2505.02060","repositories_listed":1,"syntology":null},{"url":"/paper/bersting-at-the-screams-a-benchmark-for","slug":"bersting-at-the-screams-a-benchmark-for","title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","date":"2025-04-30","arxiv_id":"2505.00059","repositories_listed":1,"syntology":null},{"url":"/paper/kimi-audio-technical-report","slug":"kimi-audio-technical-report","title":"Kimi-Audio Technical Report","date":"2025-04-25","arxiv_id":"2504.18425","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":1,"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/kimi-audio-technical-report#ran","syntology_url":"https://syntology.ai/paper/2504.18425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.18425"}},"official":{"repos":["moonshotai/kimi-audio"],"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/tinyml-for-speech-recognition","slug":"tinyml-for-speech-recognition","title":"TinyML for Speech Recognition","date":"2025-04-22","arxiv_id":"2504.16213","repositories_listed":1,"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/rnn-transducer-based-losses-for-speech","slug":"rnn-transducer-based-losses-for-speech","title":"RNN-Transducer-based Losses for Speech Recognition on Noisy Targets","date":"2025-04-09","arxiv_id":"2504.06963","repositories_listed":1,"syntology":null},{"url":"/paper/docia-an-online-document-level-context","slug":"docia-an-online-document-level-context","title":"DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation","date":"2025-04-07","arxiv_id":"2504.05122","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-named-entity-recognition-2","slug":"transformer-based-named-entity-recognition-2","title":"Transformer-Based Named Entity Recognition for Automated Server Provisioning","date":"2025-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/whispering-under-the-eaves-protecting-user","slug":"whispering-under-the-eaves-protecting-user","title":"Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems","date":"2025-04-01","arxiv_id":"2504.00858","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/whispering-under-the-eaves-protecting-user#ran","syntology_url":"https://syntology.ai/paper/2504.00858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.00858"}},"official":{"repos":["WeifeiJin/AudioShield"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/teleantifraud-28k-a-audio-text-slow-thinking","slug":"teleantifraud-28k-a-audio-text-slow-thinking","title":"TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection","date":"2025-03-31","arxiv_id":"2503.24115","repositories_listed":1,"syntology":null},{"url":"/paper/dolphin-a-large-scale-automatic-speech","slug":"dolphin-a-large-scale-automatic-speech","title":"Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages","date":"2025-03-26","arxiv_id":"2503.20212","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/whisper-speaker-identification-leveraging-pre","slug":"whisper-speaker-identification-leveraging-pre","title":"Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings","date":"2025-03-13","arxiv_id":"2503.10446","repositories_listed":1,"syntology":null},{"url":"/paper/quantization-for-openai-s-whisper-models-a","slug":"quantization-for-openai-s-whisper-models-a","title":"Quantization for OpenAI's Whisper Models: A Comparative Analysis","date":"2025-03-12","arxiv_id":"2503.09905","repositories_listed":1,"syntology":null},{"url":"/paper/lend-a-hand-semi-training-free-cued-speech","slug":"lend-a-hand-semi-training-free-cued-speech","title":"Lend a Hand: Semi Training-Free Cued Speech Recognition via MLLM-Driven Hand Modeling for Barrier-free Communication","date":"2025-03-11","arxiv_id":"2503.21785","repositories_listed":1,"syntology":null},{"url":"/paper/a-noise-robust-turn-taking-system-for-real","slug":"a-noise-robust-turn-taking-system-for-real","title":"A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experiment","date":"2025-03-08","arxiv_id":"2503.06241","repositories_listed":1,"syntology":null},{"url":"/paper/zero-avsr-zero-shot-audio-visual-speech","slug":"zero-avsr-zero-shot-audio-visual-speech","title":"Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations","date":"2025-03-08","arxiv_id":"2503.06273","repositories_listed":1,"syntology":null},{"url":"/paper/cleanmel-mel-spectrogram-enhancement-for","slug":"cleanmel-mel-spectrogram-enhancement-for","title":"CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR","date":"2025-02-27","arxiv_id":"2502.20040","repositories_listed":1,"syntology":null},{"url":"/paper/liteasr-efficient-automatic-speech","slug":"liteasr-efficient-automatic-speech","title":"LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation","date":"2025-02-27","arxiv_id":"2502.20583","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/liteasr-efficient-automatic-speech#ran","syntology_url":"https://syntology.ai/paper/2502.20583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20583"}},"official":{"repos":["efeslab/liteasr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-the-inclusivity-of-dutch-speech","slug":"improving-the-inclusivity-of-dutch-speech","title":"Improving the Inclusivity of Dutch Speech Recognition by Fine-tuning Whisper on the JASMIN-CGN Corpus","date":"2025-02-24","arxiv_id":"2502.17284","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-the-effect-of-transcription-noise","slug":"measuring-the-effect-of-transcription-noise","title":"Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks","date":"2025-02-19","arxiv_id":"2502.13645","repositories_listed":1,"syntology":null},{"url":"/paper/duplexmamba-enhancing-real-time-speech","slug":"duplexmamba-enhancing-real-time-speech","title":"DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities","date":"2025-02-16","arxiv_id":"2502.11123","repositories_listed":1,"syntology":null},{"url":"/paper/vinp-variational-bayesian-inference-with","slug":"vinp-variational-bayesian-inference-with","title":"VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification","date":"2025-02-11","arxiv_id":"2502.07205","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-representation-learning-via","slug":"audio-visual-representation-learning-via","title":"Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models","date":"2025-02-09","arxiv_id":"2502.05766","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-broadcast-media-subtitle","slug":"leveraging-broadcast-media-subtitle","title":"Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and Subtitling","date":"2025-02-05","arxiv_id":"2502.03212","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/evaluation-of-end-to-end-continuous-spanish","slug":"evaluation-of-end-to-end-continuous-spanish","title":"Evaluation of End-to-End Continuous Spanish Lipreading in Different Data Conditions","date":"2025-02-01","arxiv_id":"2502.00464","repositories_listed":1,"syntology":null},{"url":"/paper/sagalee-an-open-source-automatic-speech","slug":"sagalee-an-open-source-automatic-speech","title":"Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language","date":"2025-02-01","arxiv_id":"2502.00421","repositories_listed":1,"syntology":null},{"url":"/paper/rdmm-fine-tuned-llm-models-for-on-device","slug":"rdmm-fine-tuned-llm-models-for-on-device","title":"RDMM: Fine-Tuned LLM Models for On-Device Robotic Decision Making with Enhanced Contextual Awareness in Specific Domains","date":"2025-01-28","arxiv_id":"2501.16899","repositories_listed":1,"syntology":null},{"url":"/paper/speech-translation-refinement-using-large","slug":"speech-translation-refinement-using-large","title":"Speech Translation Refinement using Large Language Models","date":"2025-01-25","arxiv_id":"2501.15090","repositories_listed":1,"syntology":null},{"url":"/paper/fireredasr-open-source-industrial-grade","slug":"fireredasr-open-source-industrial-grade","title":"FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration","date":"2025-01-24","arxiv_id":"2501.14350","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-corrupted-prediction-for-learning","slug":"multi-task-corrupted-prediction-for-learning","title":"Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation","date":"2025-01-23","arxiv_id":"2504.18539","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-corrupted-prediction-for-learning#ran","syntology_url":"https://syntology.ai/paper/2504.18539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.18539"}},"official":{"repos":["sungnyun/cav2vec"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/osum-advancing-open-speech-understanding","slug":"osum-advancing-open-speech-understanding","title":"OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia","date":"2025-01-23","arxiv_id":"2501.13306","repositories_listed":1,"syntology":null},{"url":"/paper/flanec-exploring-flan-t5-for-post-asr-error","slug":"flanec-exploring-flan-t5-for-post-asr-error","title":"FlanEC: Exploring Flan-T5 for Post-ASR Error Correction","date":"2025-01-22","arxiv_id":"2501.12979","repositories_listed":1,"syntology":null},{"url":"/paper/pier-a-novel-metric-for-evaluating-what","slug":"pier-a-novel-metric-for-evaluating-what","title":"PIER: A Novel Metric for Evaluating What Matters in Code-Switching","date":"2025-01-16","arxiv_id":"2501.09512","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-wav2vec2-the-language-of-the-brain","slug":"teaching-wav2vec2-the-language-of-the-brain","title":"Teaching Wav2Vec2 the Language of the Brain","date":"2025-01-16","arxiv_id":"2501.09459","repositories_listed":1,"syntology":null},{"url":"/paper/selective-attention-merging-for-low-resource","slug":"selective-attention-merging-for-low-resource","title":"Selective Attention Merging for low resource tasks: A case study of Child ASR","date":"2025-01-14","arxiv_id":"2501.08468","repositories_listed":1,"syntology":null},{"url":"/paper/adacs-adaptive-normalization-for-enhanced","slug":"adacs-adaptive-normalization-for-enhanced","title":"AdaCS: Adaptive Normalization for Enhanced Code-Switching ASR","date":"2025-01-13","arxiv_id":"2501.07102","repositories_listed":1,"syntology":null},{"url":"/paper/joint-automatic-speech-recognition-and","slug":"joint-automatic-speech-recognition-and","title":"Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding","date":"2025-01-13","arxiv_id":"2501.07329","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-speech-unit-extraction-via","slug":"discrete-speech-unit-extraction-via","title":"Discrete Speech Unit Extraction via Independent Component Analysis","date":"2025-01-11","arxiv_id":"2501.06562","repositories_listed":1,"syntology":null},{"url":"/paper/comparing-self-supervised-learning-models-pre","slug":"comparing-self-supervised-learning-models-pre","title":"Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing","date":"2025-01-10","arxiv_id":"2501.05987","repositories_listed":1,"syntology":null},{"url":"/paper/fleurs-slu-a-massively-multilingual-benchmark","slug":"fleurs-slu-a-massively-multilingual-benchmark","title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","date":"2025-01-10","arxiv_id":"2501.06117","repositories_listed":1,"syntology":null},{"url":"/paper/listening-and-seeing-again-generative-error","slug":"listening-and-seeing-again-generative-error","title":"Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition","date":"2025-01-03","arxiv_id":"2501.04038","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-singlish-understanding-bridging-the","slug":"advancing-singlish-understanding-bridging-the","title":"Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models","date":"2025-01-02","arxiv_id":"2501.01034","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-read-write-policy","slug":"large-language-models-are-read-write-policy","title":"Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation","date":"2025-01-01","arxiv_id":"2501.00868","repositories_listed":1,"syntology":null},{"url":"/paper/dicow-diarization-conditioned-whisper-for","slug":"dicow-diarization-conditioned-whisper-for","title":"DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition","date":"2024-12-30","arxiv_id":"2501.00114","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-audiovisual-speech-recognition","slug":"enhancing-audiovisual-speech-recognition","title":"Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization","date":"2024-12-26","arxiv_id":"2412.19005","repositories_listed":1,"syntology":null},{"url":"/paper/mathspeech-leveraging-small-lms-for-accurate","slug":"mathspeech-leveraging-small-lms-for-accurate","title":"MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula","date":"2024-12-20","arxiv_id":"2412.15655","repositories_listed":1,"syntology":null},{"url":"/paper/streaming-keyword-spotting-boosted-by-cross","slug":"streaming-keyword-spotting-boosted-by-cross","title":"Streaming Keyword Spotting Boosted by Cross-layer Discrimination Consistency","date":"2024-12-17","arxiv_id":"2412.12635","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-adaptation-of-multilingual-models","slug":"efficient-adaptation-of-multilingual-models","title":"Efficient Adaptation of Multilingual Models for Japanese ASR","date":"2024-12-14","arxiv_id":"2412.10705","repositories_listed":1,"syntology":null},{"url":"/paper/sq-whisper-speaker-querying-based-whisper","slug":"sq-whisper-speaker-querying-based-whisper","title":"SQ-Whisper: Speaker-Querying based Whisper Model for Target-Speaker ASR","date":"2024-12-07","arxiv_id":"2412.05589","repositories_listed":1,"syntology":null}],"record_sha256":"4b625bfe7f71a1dba72b2ef62304d6a03c3726c28394b98f3d4f14648d6b5b2b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}