{"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/papers/8","list_of":"/task/speech-recognition","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":8,"pages_in_order":65,"rows_per_page":100,"rows":[701,800],"of":6433,"counts":{"archive_papers_tagged":6433,"with_a_code_link":1373,"where_syntology_ran_a_sample":196,"not_listed_spam_title":0,"listed":6433,"listed_where_code_ran":196,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":162,"every_run_a_failure_of_syntologys_instrument":34,"listed_with_a_run_with_no_instrument_failure":162,"listed_every_run_a_failure_of_syntologys_instrument":34,"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","prev":"/task/speech-recognition/papers/7","next":"/task/speech-recognition/papers/9","papers":[{"url":"/paper/deepgd-a-multi-objective-black-box-test","slug":"deepgd-a-multi-objective-black-box-test","title":"DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks","date":"2023-03-08","arxiv_id":"2303.04878","repositories_listed":1,"syntology":null},{"url":"/paper/ts-sep-joint-diarization-and-separation","slug":"ts-sep-joint-diarization-and-separation","title":"TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings","date":"2023-03-07","arxiv_id":"2303.03849","repositories_listed":1,"syntology":null},{"url":"/paper/calibrating-transformers-via-sparse-gaussian","slug":"calibrating-transformers-via-sparse-gaussian","title":"Calibrating Transformers via Sparse Gaussian Processes","date":"2023-03-04","arxiv_id":"2303.02444","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/calibrating-transformers-via-sparse-gaussian#ran","syntology_url":"https://syntology.ai/paper/2303.02444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02444"}},"official":{"repos":["chenw20/sgpa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/muavic-a-multilingual-audio-visual-corpus-for","slug":"muavic-a-multilingual-audio-visual-corpus-for","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","date":"2023-03-01","arxiv_id":"2303.00628","repositories_listed":1,"syntology":null},{"url":"/paper/brainbert-self-supervised-representation","slug":"brainbert-self-supervised-representation","title":"BrainBERT: Self-supervised representation learning for intracranial recordings","date":"2023-02-28","arxiv_id":"2302.14367","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"5 ran (of which 4 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) · 1 unverified","sample_list":"/paper/brainbert-self-supervised-representation#ran","syntology_url":"https://syntology.ai/paper/2302.14367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.14367"}},"official":{"repos":["czlwang/brainbert"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/structured-pruning-of-self-supervised-pre","slug":"structured-pruning-of-self-supervised-pre","title":"Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and Understanding","date":"2023-02-27","arxiv_id":"2302.14132","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/pre-finetuning-for-few-shot-emotional-speech","slug":"pre-finetuning-for-few-shot-emotional-speech","title":"Pre-Finetuning for Few-Shot Emotional Speech Recognition","date":"2023-02-24","arxiv_id":"2302.12921","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/readin-a-chinese-multi-task-benchmark-with","slug":"readin-a-chinese-multi-task-benchmark-with","title":"READIN: A Chinese Multi-Task Benchmark with Realistic and Diverse Input Noises","date":"2023-02-14","arxiv_id":"2302.07324","repositories_listed":1,"syntology":null},{"url":"/paper/sneaky-spikes-uncovering-stealthy-backdoor","slug":"sneaky-spikes-uncovering-stealthy-backdoor","title":"Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data","date":"2023-02-13","arxiv_id":"2302.06279","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/neural-architecture-search-insights-from-1000","slug":"neural-architecture-search-insights-from-1000","title":"Neural Architecture Search: Insights from 1000 Papers","date":"2023-01-20","arxiv_id":"2301.08727","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/olkavs-an-open-large-scale-korean-audio","slug":"olkavs-an-open-large-scale-korean-audio","title":"OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset","date":"2023-01-16","arxiv_id":"2301.06375","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/olkavs-an-open-large-scale-korean-audio#ran","syntology_url":"https://syntology.ai/paper/2301.06375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.06375"}},"official":{"repos":["iip-sogang/olkavs-avspeech"],"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/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/supervised-acoustic-embeddings-and-their","slug":"supervised-acoustic-embeddings-and-their","title":"Supervised Acoustic Embeddings And Their Transferability Across Languages","date":"2023-01-03","arxiv_id":"2301.01020","repositories_listed":1,"syntology":null},{"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/learning-to-detect-noisy-labels-using-model","slug":"learning-to-detect-noisy-labels-using-model","title":"Learning to Detect Noisy Labels Using Model-Based Features","date":"2022-12-28","arxiv_id":"2212.13767","repositories_listed":1,"syntology":null},{"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/jointly-learning-visual-and-auditory-speech","slug":"jointly-learning-visual-and-auditory-speech","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","date":"2022-12-12","arxiv_id":"2212.06246","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/lmec-learnable-multiplicative-absolute","slug":"lmec-learnable-multiplicative-absolute","title":"LMEC: Learnable Multiplicative Absolute Position Embedding Based Conformer for Speech Recognition","date":"2022-12-05","arxiv_id":"2212.02099","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/videodubber-machine-translation-with-speech","slug":"videodubber-machine-translation-with-speech","title":"VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing","date":"2022-11-30","arxiv_id":"2211.16934","repositories_listed":1,"syntology":null},{"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/on-word-error-rate-definitions-and-their","slug":"on-word-error-rate-definitions-and-their","title":"On Word Error Rate Definitions and their Efficient Computation for Multi-Speaker Speech Recognition Systems","date":"2022-11-29","arxiv_id":"2211.16112","repositories_listed":1,"syntology":null},{"url":"/paper/mask-the-correct-tokens-an-embarrassingly","slug":"mask-the-correct-tokens-an-embarrassingly","title":"Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction","date":"2022-11-23","arxiv_id":"2211.13252","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/streaming-joint-speech-recognition-and","slug":"streaming-joint-speech-recognition-and","title":"Streaming Joint Speech Recognition and Disfluency Detection","date":"2022-11-16","arxiv_id":"2211.08726","repositories_listed":1,"syntology":null},{"url":"/paper/improving-children-s-speech-recognition-by","slug":"improving-children-s-speech-recognition-by","title":"Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech Representations","date":"2022-11-14","arxiv_id":"2211.07769","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/comparative-layer-wise-analysis-of-self","slug":"comparative-layer-wise-analysis-of-self","title":"Comparative layer-wise analysis of self-supervised speech models","date":"2022-11-08","arxiv_id":"2211.03929","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/speech-text-based-multi-modal-training-with","slug":"speech-text-based-multi-modal-training-with","title":"Speech-text based multi-modal training with bidirectional attention for improved speech recognition","date":"2022-11-01","arxiv_id":"2211.00325","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/fast-and-parallel-decoding-for-transducer","slug":"fast-and-parallel-decoding-for-transducer","title":"Fast and parallel decoding for transducer","date":"2022-10-31","arxiv_id":"2211.00484","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/improved-acoustic-to-articulatory-inversion","slug":"improved-acoustic-to-articulatory-inversion","title":"Improved acoustic-to-articulatory inversion using representations from pretrained self-supervised learning models","date":"2022-10-30","arxiv_id":"2210.16871","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-spoken-language-understanding-with","slug":"end-to-end-spoken-language-understanding-with","title":"End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator","date":"2022-10-29","arxiv_id":"2210.16554","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/evaluating-context-invariance-in-unsupervised","slug":"evaluating-context-invariance-in-unsupervised","title":"Evaluating context-invariance in unsupervised speech representations","date":"2022-10-27","arxiv_id":"2210.15775","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/generalizing-in-the-real-world-with","slug":"generalizing-in-the-real-world-with","title":"Generalizing in the Real World with Representation Learning","date":"2022-10-18","arxiv_id":"2210.09925","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/transfusion-transcribing-speech-with","slug":"transfusion-transcribing-speech-with","title":"TransFusion: Transcribing Speech with Multinomial Diffusion","date":"2022-10-14","arxiv_id":"2210.07677","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/speechlm-enhanced-speech-pre-training-with","slug":"speechlm-enhanced-speech-pre-training-with","title":"SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data","date":"2022-09-30","arxiv_id":"2209.15329","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-affective-vocal-bursts-with","slug":"predicting-affective-vocal-bursts-with","title":"Predicting Affective Vocal Bursts with Finetuned wav2vec 2.0","date":"2022-09-27","arxiv_id":"2209.13146","repositories_listed":1,"syntology":null},{"url":"/paper/liquid-structural-state-space-models","slug":"liquid-structural-state-space-models","title":"Liquid Structural State-Space Models","date":"2022-09-26","arxiv_id":"2209.12951","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/hapi-a-large-scale-longitudinal-dataset-of","slug":"hapi-a-large-scale-longitudinal-dataset-of","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","date":"2022-09-18","arxiv_id":"2209.08443","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-natural-language-generation-for-task","slug":"adaptive-natural-language-generation-for-task","title":"Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning","date":"2022-09-16","arxiv_id":"2209.07873","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/accented-speech-recognition-under-the-indian","slug":"accented-speech-recognition-under-the-indian","title":"Goodness of Pronunciation Pipelines for OOV Problem","date":"2022-09-08","arxiv_id":"2209.03787","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/asr2k-speech-recognition-for-around-2000","slug":"asr2k-speech-recognition-for-around-2000","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","date":"2022-09-06","arxiv_id":"2209.02842","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/bayesian-neural-network-language-modeling-for","slug":"bayesian-neural-network-language-modeling-for","title":"Bayesian Neural Network Language Modeling for Speech Recognition","date":"2022-08-28","arxiv_id":"2208.13259","repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-neural-network-cnn-to-reduce","slug":"convolutional-neural-network-cnn-to-reduce","title":"Convolutional Neural Network (CNN) to reduce construction loss in JPEG compression caused by Discrete Fourier Transform (DFT)","date":"2022-08-26","arxiv_id":"2209.03475","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/speaker-adaptive-lip-reading-with-user","slug":"speaker-adaptive-lip-reading-with-user","title":"Speaker-adaptive Lip Reading with User-dependent Padding","date":"2022-08-09","arxiv_id":"2208.04498","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}],"record_sha256":"decde86f49ff54ad76505339b79ca17a1cd9fad077b5268b46fa163aaeb3afad","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}