{"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/7","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":7,"pages_in_order":32,"rows_per_page":100,"rows":[601,700],"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/6","next":"/task/automatic-speech-recognition-2/papers/8","papers":[{"url":"/paper/pychain-a-fully-parallelized-pytorch","slug":"pychain-a-fully-parallelized-pytorch","title":"PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR","date":"2020-05-20","arxiv_id":"2005.09824","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-monotonic-multihead-attention-for","slug":"enhancing-monotonic-multihead-attention-for","title":"Enhancing Monotonic Multihead Attention for Streaming ASR","date":"2020-05-19","arxiv_id":"2005.09394","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/enhancing-monotonic-multihead-attention-for#ran","syntology_url":"https://syntology.ai/paper/2005.09394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.09394"}},"official":{"repos":["hirofumi0810/neural_sp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-adversarial-training-data","slug":"generative-adversarial-training-data","title":"Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09256","repositories_listed":1,"syntology":null},{"url":"/paper/improved-noisy-student-training-for-automatic","slug":"improved-noisy-student-training-for-automatic","title":"Improved Noisy Student Training for Automatic Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09629","repositories_listed":1,"syntology":null},{"url":"/paper/investigations-on-phoneme-based-end-to-end","slug":"investigations-on-phoneme-based-end-to-end","title":"A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models","date":"2020-05-19","arxiv_id":"2005.09336","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-pseudo-labeling-for-speech","slug":"iterative-pseudo-labeling-for-speech","title":"Iterative Pseudo-Labeling for Speech Recognition","date":"2020-05-19","arxiv_id":"2005.09267","repositories_listed":1,"syntology":null},{"url":"/paper/quaternion-neural-networks-for-multi-channel","slug":"quaternion-neural-networks-for-multi-channel","title":"Quaternion Neural Networks for Multi-channel Distant Speech Recognition","date":"2020-05-18","arxiv_id":"2005.08566","repositories_listed":1,"syntology":null},{"url":"/paper/coupled-training-of-sequence-to-sequence","slug":"coupled-training-of-sequence-to-sequence","title":"Coupled Training of Sequence-to-Sequence Models for Accented Speech Recognition","date":"2020-05-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ctc-synchronous-training-for-monotonic","slug":"ctc-synchronous-training-for-monotonic","title":"CTC-synchronous Training for Monotonic Attention Model","date":"2020-05-10","arxiv_id":"2005.04712","repositories_listed":1,"syntology":null},{"url":"/paper/a-convolutional-neural-network-model-of-human","slug":"a-convolutional-neural-network-model-of-human","title":"A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applications","date":"2020-04-30","arxiv_id":"2004.14832","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-instructional-videos-probing-for-more","slug":"beyond-instructional-videos-probing-for-more","title":"Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube","date":"2020-04-29","arxiv_id":"2004.14338","repositories_listed":1,"syntology":null},{"url":"/paper/espnet-st-all-in-one-speech-translation","slug":"espnet-st-all-in-one-speech-translation","title":"ESPnet-ST: All-in-One Speech Translation Toolkit","date":"2020-04-21","arxiv_id":"2004.10234","repositories_listed":1,"syntology":null},{"url":"/paper/clovacall-korean-goal-oriented-dialog-speech","slug":"clovacall-korean-goal-oriented-dialog-speech","title":"ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers","date":"2020-04-20","arxiv_id":"2004.09367","repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-grapheme-to-phoneme-1","slug":"transformer-based-grapheme-to-phoneme-1","title":"Transformer based Grapheme-to-Phoneme Conversion","date":"2020-04-14","arxiv_id":"2004.06338","repositories_listed":1,"syntology":null},{"url":"/paper/morfessor-emprune-improved-subword","slug":"morfessor-emprune-improved-subword","title":"Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning","date":"2020-03-06","arxiv_id":"2003.03131","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-processing-advancements-by","slug":"natural-language-processing-advancements-by","title":"Natural Language Processing Advancements By Deep Learning: A Survey","date":"2020-03-02","arxiv_id":"2003.01200","repositories_listed":1,"syntology":null},{"url":"/paper/skinaugment-auto-encoding-speaker-conversions","slug":"skinaugment-auto-encoding-speaker-conversions","title":"SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation","date":"2020-02-27","arxiv_id":"2002.12231","repositories_listed":1,"syntology":null},{"url":"/paper/attentional-speech-recognition-models","slug":"attentional-speech-recognition-models","title":"Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances","date":"2020-02-12","arxiv_id":"2002.05150","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-speech-separation-dataset-and","slug":"continuous-speech-separation-dataset-and","title":"Continuous speech separation: dataset and analysis","date":"2020-01-30","arxiv_id":"2001.11482","repositories_listed":1,"syntology":null},{"url":"/paper/deep-xi-as-a-front-end-for-robust-automatic","slug":"deep-xi-as-a-front-end-for-robust-automatic","title":"Deep Xi as a Front-End for Robust Automatic Speech Recognition","date":"2020-01-28","arxiv_id":"1906.07319","repositories_listed":1,"syntology":null},{"url":"/paper/submodular-rank-aggregation-on-score-based","slug":"submodular-rank-aggregation-on-score-based","title":"Submodular Rank Aggregation on Score-based Permutations for Distributed Automatic Speech Recognition","date":"2020-01-27","arxiv_id":"2001.10529","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-labeling-approach-to-the-task-of","slug":"sequence-labeling-approach-to-the-task-of","title":"Sequence Labeling Approach to the Task of Sentence Boundary Detection","date":"2020-01-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generating-synthetic-audio-data-for-attention","slug":"generating-synthetic-audio-data-for-attention","title":"Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems","date":"2019-12-19","arxiv_id":"1912.09257","repositories_listed":1,"syntology":null},{"url":"/paper/synchronous-speech-recognition-and-speech-to","slug":"synchronous-speech-recognition-and-speech-to","title":"Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding","date":"2019-12-16","arxiv_id":"1912.07240","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-mask-for-transformer-based-end-to","slug":"semantic-mask-for-transformer-based-end-to","title":"Semantic Mask for Transformer based End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.03010","repositories_listed":1,"syntology":null},{"url":"/paper/deep-contextualized-acoustic-representations","slug":"deep-contextualized-acoustic-representations","title":"Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition","date":"2019-12-03","arxiv_id":"1912.01679","repositories_listed":1,"syntology":null},{"url":"/paper/improving-voice-separation-by-incorporating","slug":"improving-voice-separation-by-incorporating","title":"Improving Voice Separation by Incorporating End-to-end Speech Recognition","date":"2019-11-29","arxiv_id":"1911.12928","repositories_listed":1,"syntology":null},{"url":"/paper/kurdish-sorani-speech-to-text-presenting-an","slug":"kurdish-sorani-speech-to-text-presenting-an","title":"Kurdish (Sorani) Speech to Text: Presenting an Experimental Dataset","date":"2019-11-29","arxiv_id":"1911.13087","repositories_listed":1,"syntology":null},{"url":"/paper/deep-spiking-neural-networks-for-large","slug":"deep-spiking-neural-networks-for-large","title":"Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition","date":"2019-11-19","arxiv_id":"1911.08373","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-to-sequence-automatic-speech","slug":"sequence-to-sequence-automatic-speech","title":"Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding","date":"2019-10-28","arxiv_id":"1910.12740","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-the-impact-of-speaker-localization","slug":"analyzing-the-impact-of-speaker-localization","title":"Analyzing the impact of speaker localization errors on speech separation for automatic speech recognition","date":"2019-10-24","arxiv_id":"1910.11114","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-end-to-end-speech-translation","slug":"multilingual-end-to-end-speech-translation","title":"Multilingual End-to-End Speech Translation","date":"2019-10-01","arxiv_id":"1910.00254","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":1,"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/multilingual-end-to-end-speech-translation#ran","syntology_url":"https://syntology.ai/paper/1910.00254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00254"}},"official":{"repos":["espnet/espnet"],"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/improving-rnn-transducer-modeling-for-end-to","slug":"improving-rnn-transducer-modeling-for-end-to","title":"Improving RNN Transducer Modeling for End-to-End Speech Recognition","date":"2019-09-26","arxiv_id":"1909.12415","repositories_listed":1,"syntology":null},{"url":"/paper/espresso-a-fast-end-to-end-neural-speech","slug":"espresso-a-fast-end-to-end-neural-speech","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","date":"2019-09-18","arxiv_id":"1909.08723","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":1,"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/espresso-a-fast-end-to-end-neural-speech#ran","syntology_url":"https://syntology.ai/paper/1909.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08723"}},"official":{"repos":["freewym/espresso"],"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/nemo-a-toolkit-for-building-ai-applications","slug":"nemo-a-toolkit-for-building-ai-applications","title":"NeMo: a toolkit for building AI applications using Neural Modules","date":"2019-09-14","arxiv_id":"1909.09577","repositories_listed":1,"syntology":null},{"url":"/paper/personalizing-asr-for-dysarthric-and-accented","slug":"personalizing-asr-for-dysarthric-and-accented","title":"Personalizing ASR for Dysarthric and Accented Speech with Limited Data","date":"2019-07-31","arxiv_id":"1907.13511","repositories_listed":1,"syntology":null},{"url":"/paper/mass-a-large-and-clean-multilingual-corpus-of","slug":"mass-a-large-and-clean-multilingual-corpus-of","title":"MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible","date":"2019-07-30","arxiv_id":"1907.12895","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-phonetic-and-graphemic","slug":"analyzing-phonetic-and-graphemic","title":"Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition","date":"2019-07-09","arxiv_id":"1907.04224","repositories_listed":1,"syntology":null},{"url":"/paper/guided-source-separation-meets-a-strong-asr","slug":"guided-source-separation-meets-a-strong-asr","title":"Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR","date":"2019-05-29","arxiv_id":"1905.12230","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-audio-signal-processing","slug":"deep-learning-for-audio-signal-processing","title":"Deep Learning for Audio Signal Processing","date":"2019-04-30","arxiv_id":"1905.00078","repositories_listed":1,"syntology":null},{"url":"/paper/realizing-petabyte-scale-acoustic-modeling","slug":"realizing-petabyte-scale-acoustic-modeling","title":"Realizing Petabyte Scale Acoustic Modeling","date":"2019-04-24","arxiv_id":"1904.10584","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-speech-domain-adaptation-based","slug":"unsupervised-speech-domain-adaptation-based","title":"Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition","date":"2019-04-12","arxiv_id":"1904.06086","repositories_listed":1,"syntology":null},{"url":"/paper/spoken-language-intent-detection-using","slug":"spoken-language-intent-detection-using","title":"Spoken Language Intent Detection using Confusion2Vec","date":"2019-04-07","arxiv_id":"1904.03576","repositories_listed":1,"syntology":null},{"url":"/paper/imperceptible-robust-and-targeted-adversarial","slug":"imperceptible-robust-and-targeted-adversarial","title":"Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition","date":"2019-03-22","arxiv_id":"1903.10346","repositories_listed":1,"syntology":null},{"url":"/paper/audiovisual-speaker-tracking-using-nonlinear","slug":"audiovisual-speaker-tracking-using-nonlinear","title":"Audiovisual Speaker Tracking using Nonlinear Dynamical Systems with Dynamic Stream Weights","date":"2019-03-14","arxiv_id":"1903.06031","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-effects-of-word","slug":"investigating-the-effects-of-word","title":"Investigating the Effects of Word Substitution Errors on Sentence Embeddings","date":"2018-11-16","arxiv_id":"1811.07021","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-grounding-for-sequence-to-sequence","slug":"multimodal-grounding-for-sequence-to-sequence","title":"Multimodal Grounding for Sequence-to-Sequence Speech Recognition","date":"2018-11-09","arxiv_id":"1811.03865","repositories_listed":1,"syntology":null},{"url":"/paper/language-modeling-for-code-switching","slug":"language-modeling-for-code-switching","title":"Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative Training","date":"2018-10-28","arxiv_id":"1810.11895","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-on-high-resource-speech","slug":"pre-training-on-high-resource-speech","title":"Pre-training on high-resource speech recognition improves low-resource speech-to-text translation","date":"2018-09-05","arxiv_id":"1809.01431","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-adapt-a-meta-learning-approach","slug":"learning-to-adapt-a-meta-learning-approach","title":"Learning to adapt: a meta-learning approach for speaker adaptation","date":"2018-08-30","arxiv_id":"1808.10239","repositories_listed":1,"syntology":null},{"url":"/paper/wisebe-window-based-sentence-boundary","slug":"wisebe-window-based-sentence-boundary","title":"WiSeBE: Window-based Sentence Boundary Evaluation","date":"2018-08-27","arxiv_id":"1808.08850","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-techniques-for-language-model","slug":"a-comparison-of-techniques-for-language-model","title":"A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition","date":"2018-07-27","arxiv_id":"1807.10857","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-keyword-spotting-for-visual-speech","slug":"zero-shot-keyword-spotting-for-visual-speech","title":"Zero-shot keyword spotting for visual speech recognition in-the-wild","date":"2018-07-23","arxiv_id":"1807.08469","repositories_listed":1,"syntology":null},{"url":"/paper/a-comparison-of-adaptation-techniques-and","slug":"a-comparison-of-adaptation-techniques-and","title":"A Comparison of Adaptation Techniques and Recurrent Neural Network Architectures","date":"2018-07-12","arxiv_id":"1807.06441","repositories_listed":1,"syntology":null},{"url":"/paper/word-error-rate-estimation-for-speech","slug":"word-error-rate-estimation-for-speech","title":"Word Error Rate Estimation for Speech Recognition: e-WER","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/quaternion-convolutional-neural-networks-for-1","slug":"quaternion-convolutional-neural-networks-for-1","title":"Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition","date":"2018-06-20","arxiv_id":"1806.07789","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-dnns-and-its-ensembles-on-the-timit","slug":"recurrent-dnns-and-its-ensembles-on-the-timit","title":"Recurrent DNNs and its Ensembles on the TIMIT Phone Recognition Task","date":"2018-06-19","arxiv_id":"1806.07186","repositories_listed":1,"syntology":null},{"url":"/paper/lstm-benchmarks-for-deep-learning-frameworks","slug":"lstm-benchmarks-for-deep-learning-frameworks","title":"LSTM Benchmarks for Deep Learning Frameworks","date":"2018-06-05","arxiv_id":"1806.01818","repositories_listed":1,"syntology":null},{"url":"/paper/targeted-adversarial-examples-for-black-box","slug":"targeted-adversarial-examples-for-black-box","title":"Targeted Adversarial Examples for Black Box Audio Systems","date":"2018-05-20","arxiv_id":"1805.07820","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/targeted-adversarial-examples-for-black-box#ran","syntology_url":"https://syntology.ai/paper/1805.07820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07820"}},"official":{"repos":["rtaori/Black-Box-Audio"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/syllable-based-sequence-to-sequence-speech","slug":"syllable-based-sequence-to-sequence-speech","title":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese","date":"2018-04-28","arxiv_id":"1804.10752","repositories_listed":1,"syntology":null},{"url":"/paper/attentive-sequence-to-sequence-learning-for","slug":"attentive-sequence-to-sequence-learning-for","title":"Attentive Sequence-to-Sequence Learning for Diacritic Restoration of Yorùbá Language Text","date":"2018-04-03","arxiv_id":"1804.00832","repositories_listed":1,"syntology":null},{"url":"/paper/light-gated-recurrent-units-for-speech","slug":"light-gated-recurrent-units-for-speech","title":"Light Gated Recurrent Units for Speech Recognition","date":"2018-03-26","arxiv_id":"1803.10225","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-librispeech-with-french","slug":"augmenting-librispeech-with-french","title":"Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation","date":"2018-02-09","arxiv_id":"1802.03142","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-past-mistakes-improving","slug":"learning-from-past-mistakes-improving","title":"Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling","date":"2018-02-07","arxiv_id":"1802.02607","repositories_listed":1,"syntology":null},{"url":"/paper/did-you-hear-that-adversarial-examples","slug":"did-you-hear-that-adversarial-examples","title":"Did you hear that? Adversarial Examples Against Automatic Speech Recognition","date":"2018-01-02","arxiv_id":"1801.00554","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-hidden-representations-in-end-to","slug":"analyzing-hidden-representations-in-end-to","title":"Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems","date":"2017-09-13","arxiv_id":"1709.04482","repositories_listed":1,"syntology":null},{"url":"/paper/spoken-english-intelligibility-remediation","slug":"spoken-english-intelligibility-remediation","title":"Spoken English Intelligibility Remediation with PocketSphinx Alignment and Feature Extraction Improves Substantially over the State of the Art","date":"2017-09-06","arxiv_id":"1709.01713","repositories_listed":1,"syntology":null},{"url":"/paper/language-identification-using-deep","slug":"language-identification-using-deep","title":"Language Identification Using Deep Convolutional Recurrent Neural Networks","date":"2017-08-16","arxiv_id":"1708.04811","repositories_listed":1,"syntology":null},{"url":"/paper/massively-multilingual-neural-grapheme-to","slug":"massively-multilingual-neural-grapheme-to","title":"Massively Multilingual Neural Grapheme-to-Phoneme Conversion","date":"2017-08-04","arxiv_id":"1708.01464","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-submodular-rank-aggregation-on","slug":"unsupervised-submodular-rank-aggregation-on","title":"Unsupervised Submodular Rank Aggregation on Score-based Permutations","date":"2017-07-04","arxiv_id":"1707.01166","repositories_listed":1,"syntology":null},{"url":"/paper/improving-lstm-ctc-based-asr-performance-in","slug":"improving-lstm-ctc-based-asr-performance-in","title":"Improving LSTM-CTC based ASR performance in domains with limited training data","date":"2017-07-03","arxiv_id":"1707.00722","repositories_listed":1,"syntology":null},{"url":"/paper/joint-ctcattention-decoding-for-end-to-end","slug":"joint-ctcattention-decoding-for-end-to-end","title":"Joint CTC/attention decoding for end-to-end speech recognition","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/speech-based-visual-question-answering","slug":"speech-based-visual-question-answering","title":"Speech-Based Visual Question Answering","date":"2017-05-01","arxiv_id":"1705.00464","repositories_listed":1,"syntology":null},{"url":"/paper/towards-end-to-end-speech-recognition-with","slug":"towards-end-to-end-speech-recognition-with","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","date":"2017-01-10","arxiv_id":"1701.02720","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/towards-end-to-end-speech-recognition-with#ran","syntology_url":"https://syntology.ai/paper/1701.02720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.02720"}},"official":null}},{"url":"/paper/audio-segmentation-for-robust-real-time","slug":"audio-segmentation-for-robust-real-time","title":"Audio Segmentation for Robust Real-Time Speech Recognition Based on Neural Networks","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/collecting-resources-in-sub-saharan-african","slug":"collecting-resources-in-sub-saharan-african","title":"Collecting Resources in Sub-Saharan African Languages for Automatic Speech Recognition: a Case Study of Wolof","date":"2016-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/character-level-neural-translation-for","slug":"character-level-neural-translation-for","title":"Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project","date":"2016-04-05","arxiv_id":"1604.01221","repositories_listed":1,"syntology":null},{"url":null,"slug":"nonverbaltts-a-public-english-corpus-of-text","title":"NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech","date":"2025-07-17","arxiv_id":"2507.13155","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-specific-audio-coding-for-machines","title":"Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine","date":"2025-07-17","arxiv_id":"2507.12701","repositories_listed":0,"syntology":null},{"url":null,"slug":"whisperkit-on-device-real-time-asr-with","title":"WhisperKit: On-device Real-time ASR with Billion-Scale Transformers","date":"2025-07-14","arxiv_id":"2507.10860","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualspeaker-visually-guided-3d-avatar-lip","title":"VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis","date":"2025-07-08","arxiv_id":"2507.06060","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-target-speaker-based-overlap","title":"Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR","date":"2025-06-25","arxiv_id":"2506.20288","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-generated-song-detection-via-lyrics","title":"AI-Generated Song Detection via Lyrics Transcripts","date":"2025-06-23","arxiv_id":"2506.18488","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-spoken-grammatical-error","title":"End-to-End Spoken Grammatical Error Correction","date":"2025-06-23","arxiv_id":"2506.18532","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-transcription-bottleneck-fine","title":"Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages","date":"2025-06-20","arxiv_id":"2506.17459","repositories_listed":0,"syntology":null},{"url":null,"slug":"lm-spt-lm-aligned-semantic-distillation-for","title":"LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization","date":"2025-06-20","arxiv_id":"2506.16738","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-space-models-in-efficient-whispered-and","title":"State-Space Models in Efficient Whispered and Multi-dialect Speech Recognition","date":"2025-06-20","arxiv_id":"2506.16969","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-biases-in","title":"Automatic Speech Recognition Biases in Newcastle English: an Error Analysis","date":"2025-06-19","arxiv_id":"2506.16558","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-practical-aspects-of-end-to-end","title":"Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios","date":"2025-06-17","arxiv_id":"2506.14204","repositories_listed":0,"syntology":null},{"url":"/paper/unifying-streaming-and-non-streaming","slug":"unifying-streaming-and-non-streaming","title":"Unifying Streaming and Non-streaming Zipformer-based ASR","date":"2025-06-17","arxiv_id":"2506.14434","repositories_listed":0,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unifying-streaming-and-non-streaming#ran","syntology_url":"https://syntology.ai/paper/2506.14434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14434"}},"official":null}},{"url":null,"slug":"bi-directional-context-enhanced-speech-large","title":"Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR","date":"2025-06-16","arxiv_id":"2506.13396","repositories_listed":0,"syntology":null},{"url":null,"slug":"but-system-for-the-mlc-slm-challenge","title":"BUT System for the MLC-SLM Challenge","date":"2025-06-16","arxiv_id":"2506.13414","repositories_listed":0,"syntology":null},{"url":null,"slug":"ntu-speechlab-llm-based-multilingual-asr","title":"NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025","date":"2025-06-16","arxiv_id":"2506.13339","repositories_listed":0,"syntology":null},{"url":null,"slug":"seewo-s-submission-to-mlc-slm-lessons-learned","title":"Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models","date":"2025-06-16","arxiv_id":"2506.13300","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-automatic-transcription-of-child","title":"Enabling automatic transcription of child-centered audio recordings from real-world environments","date":"2025-06-13","arxiv_id":"2506.11747","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-and-robust-multi-channel-end-to","title":"Lightweight and Robust Multi-Channel End-to-End Speech Recognition with Spherical Harmonic Transform","date":"2025-06-13","arxiv_id":"2506.11630","repositories_listed":0,"syntology":null},{"url":null,"slug":"simphon-speech-test-a-data-driven-method-for","title":"(SimPhon Speech Test): A Data-Driven Method for In Silico Design and Validation of a Phonetically Balanced Speech Test","date":"2025-06-13","arxiv_id":"2506.11620","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairasr-fair-audio-contrastive-learning-for","title":"FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition","date":"2025-06-12","arxiv_id":"2506.10747","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-named-entity-transcription-with","title":"Improving Named Entity Transcription with Contextual LLM-based Revision","date":"2025-06-12","arxiv_id":"2506.10779","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-asr-and-speaker-role-tagging-with","title":"Joint ASR and Speaker Role Tagging with Serialized Output Training","date":"2025-06-12","arxiv_id":"2506.10349","repositories_listed":0,"syntology":null}],"record_sha256":"ceedefdd65ae75cfc339e2f7b17a0f3c899c64ec3c013588fa9203fa5a1ff5cc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}