{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/automatic-speech-recognition/papers/16","list_of":"/task/automatic-speech-recognition","task":"Automatic Speech Recognition (ASR)","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":16,"pages_in_order":31,"rows_per_page":100,"rows":[1501,1600],"of":3012,"counts":{"archive_papers_tagged":3012,"with_a_code_link":622,"where_syntology_ran_a_sample":77,"not_listed_spam_title":0,"listed":3012,"listed_where_code_ran":77,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":64,"every_run_a_failure_of_syntologys_instrument":13,"listed_with_a_run_with_no_instrument_failure":64,"listed_every_run_a_failure_of_syntologys_instrument":13,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/automatic-speech-recognition","prev":"/task/automatic-speech-recognition/papers/15","next":"/task/automatic-speech-recognition/papers/17","papers":[{"url":null,"slug":"investigating-the-impact-of-cross-lingual","title":"Investigating the Impact of Cross-lingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition","date":"2022-07-07","arxiv_id":"2207.03390","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-streaming-end-to-end-asr-on","title":"Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies","date":"2022-07-06","arxiv_id":"2207.02495","repositories_listed":0,"syntology":null},{"url":null,"slug":"compute-cost-amortized-transformer-for","title":"Compute Cost Amortized Transformer for Streaming ASR","date":"2022-07-05","arxiv_id":"2207.02393","repositories_listed":0,"syntology":null},{"url":null,"slug":"vietnamese-capitalization-and-punctuation","title":"Vietnamese Capitalization and Punctuation Recovery Models","date":"2022-07-04","arxiv_id":"2207.01312","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-acoustic-contextual-representation","title":"Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR","date":"2022-07-03","arxiv_id":"2207.01039","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-transformer-based-conversational","title":"Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism","date":"2022-07-02","arxiv_id":"2207.00883","repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-constrained-pointer-generator-with-graph","title":"Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition","date":"2022-07-02","arxiv_id":"2207.00857","repositories_listed":0,"syntology":null},{"url":null,"slug":"activity-focused-speech-recognition-of","title":"Activity focused Speech Recognition of Preschool Children in Early Childhood Classrooms","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-effect-of-dialect-mismatched","title":"Exploring the Effect of Dialect Mismatched Language Models in Telugu Automatic Speech Recognition","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-low-resource-speech-recognition","title":"Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Training","date":"2022-07-01","arxiv_id":"2207.00659","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-autoregressive-chinese-asr-error","title":"Non-Autoregressive Chinese ASR Error Correction with Phonological Training","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"updating-only-encoders-prevents-catastrophic","title":"Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models","date":"2022-07-01","arxiv_id":"2207.00216","repositories_listed":0,"syntology":null},{"url":null,"slug":"fearless-feature-refinement-loss-for","title":"FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition","date":"2022-06-30","arxiv_id":"2206.15056","repositories_listed":0,"syntology":null},{"url":null,"slug":"space-efficient-representation-of-entity","title":"Space-Efficient Representation of Entity-centric Query Language Models","date":"2022-06-29","arxiv_id":"2206.14885","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-thuee-system-description-for-the-iarpa","title":"The THUEE System Description for the IARPA OpenASR21 Challenge","date":"2022-06-29","arxiv_id":"2206.14660","repositories_listed":0,"syntology":null},{"url":null,"slug":"bengali-common-voice-speech-dataset-for","title":"Bengali Common Voice Speech Dataset for Automatic Speech Recognition","date":"2022-06-28","arxiv_id":"2206.14053","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-and-opportunities-in-multi-device","title":"Challenges and Opportunities in Multi-device Speech Processing","date":"2022-06-27","arxiv_id":"2206.15432","repositories_listed":0,"syntology":null},{"url":null,"slug":"talcs-an-open-source-mandarin-english-code","title":"TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline","date":"2022-06-27","arxiv_id":"2206.13135","repositories_listed":0,"syntology":null},{"url":null,"slug":"annotated-speech-corpus-for-low-resource","title":"Annotated Speech Corpus for Low Resource Indian Languages: Awadhi, Bhojpuri, Braj and Magahi","date":"2022-06-26","arxiv_id":"2206.12931","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-training-recipe-for-a-robust","title":"Improving the Training Recipe for a Robust Conformer-based Hybrid Model","date":"2022-06-26","arxiv_id":"2206.12955","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-auxiliary-learning-for-low-resource","title":"Meta Auxiliary Learning for Low-resource Spoken Language Understanding","date":"2022-06-26","arxiv_id":"2206.12774","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-comparison-of-encoders-for-attention-based","title":"On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode","date":"2022-06-26","arxiv_id":"2206.12829","repositories_listed":0,"syntology":null},{"url":null,"slug":"confidence-score-based-conformer-speaker","title":"Confidence Score Based Conformer Speaker Adaptation for Speech Recognition","date":"2022-06-24","arxiv_id":"2206.12045","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-pass-decoding-and-cross-adaptation-based","title":"Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems","date":"2022-06-23","arxiv_id":"2206.11596","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-baseline-for-domain-adaptation-in-1","title":"A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data","date":"2022-06-22","arxiv_id":"2206.13240","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervision-guided-codebooks-for-masked","title":"Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training","date":"2022-06-21","arxiv_id":"2206.10125","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-makerere-radio-speech-corpus-a-luganda","title":"The Makerere Radio Speech Corpus: A Luganda Radio Corpus for Automatic Speech Recognition","date":"2022-06-20","arxiv_id":"2206.09790","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-robust-low-resource","title":"Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping","date":"2022-06-19","arxiv_id":"2206.09396","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-federated-learning-for-asr-with-non","title":"Decoupled Federated Learning for ASR with Non-IID Data","date":"2022-06-18","arxiv_id":"2206.09102","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-ctc-triggered-siamese-network-with-spatial","title":"A CTC Triggered Siamese Network with Spatial-Temporal Dropout for Speech Recognition","date":"2022-06-16","arxiv_id":"2206.08031","repositories_listed":0,"syntology":null},{"url":null,"slug":"draft-a-novel-framework-to-reduce-domain","title":"DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children's ASR","date":"2022-06-16","arxiv_id":"2206.07931","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-cross-domain-and-cross-lingual","title":"Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition","date":"2022-06-15","arxiv_id":"2206.07327","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-capabilities-of-monolingual-audio","title":"Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech","date":"2022-06-15","arxiv_id":"2206.07627","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-language-model-for-end-to-end-speech","title":"Residual Language Model for End-to-end Speech Recognition","date":"2022-06-15","arxiv_id":"2206.07430","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-zevomos-entry-to-voicemos-challenge-2022","title":"The ZevoMOS entry to VoiceMOS Challenge 2022","date":"2022-06-15","arxiv_id":"2206.07448","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-automatic-speech","title":"Transformer-based Automatic Speech Recognition of Formal and Colloquial Czech in MALACH Project","date":"2022-06-15","arxiv_id":"2206.07666","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-zero-oracle-word-error-rate-on-the","title":"Toward Zero Oracle Word Error Rate on the Switchboard Benchmark","date":"2022-06-13","arxiv_id":"2206.06192","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-ensemble-features-of-self","title":"Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition","date":"2022-06-11","arxiv_id":"2206.05518","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-based-out-of-vocabulary-word-recovery","title":"Context-based out-of-vocabulary word recovery for ASR systems in Indian languages","date":"2022-06-09","arxiv_id":"2206.04305","repositories_listed":0,"syntology":null},{"url":null,"slug":"face-dubbing-lip-synchronous-voice-preserving","title":"Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos","date":"2022-06-09","arxiv_id":"2206.04523","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-encoder-decoder-self-supervised-pre","title":"Joint Encoder-Decoder Self-Supervised Pre-training for ASR","date":"2022-06-09","arxiv_id":"2206.04465","repositories_listed":0,"syntology":null},{"url":null,"slug":"legonn-building-modular-encoder-decoder","title":"LegoNN: Building Modular Encoder-Decoder Models","date":"2022-06-07","arxiv_id":"2206.03318","repositories_listed":0,"syntology":null},{"url":null,"slug":"fednst-federated-noisy-student-training-for","title":"FedNST: Federated Noisy Student Training for Automatic Speech Recognition","date":"2022-06-06","arxiv_id":"2206.02797","repositories_listed":0,"syntology":null},{"url":null,"slug":"pronunciation-dictionary-free-multilingual","title":"Pronunciation Dictionary-Free Multilingual Speech Synthesis by Combining Unsupervised and Supervised Phonetic Representations","date":"2022-06-02","arxiv_id":"2206.00951","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semi-automated-live-interlingual","title":"A Semi-Automated Live Interlingual Communication Workflow Featuring Intralingual Respeaking: Evaluation and Benchmarking","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-for-irish-the","title":"Automatic Speech Recognition for Irish: the ABAIR-ÉIST System","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bea-base-a-benchmark-for-asr-of-spontaneous-1","title":"BEA-Base: A Benchmark for ASR of Spontaneous Hungarian","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-open-source-speech-technology-for","title":"Building Open-source Speech Technology for Low-resource Minority Languages with SáMi as an Example – Tools, Methods and Experiments","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-speech-recognition-needs-data","title":"Conversational Speech Recognition Needs Data? Experiments with Austrian German","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-automatic-speech-recognition-for","title":"Developing Automatic Speech Recognition for Scottish Gaelic","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-automatic-speech-recognition","title":"Development of Automatic Speech Recognition for the Documentation of Cook Islands Māori","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-off-the-shelf-speech-1","title":"Evaluation of Off-the-shelf Speech Recognizers on Different Accents in a Dialogue Domain","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-synthetic-clinical-speech-data","title":"Generating Synthetic Clinical Speech Data through Simulated ASR Deletion Error","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"huqariq-a-multilingual-speech-corpus-of-1","title":"Huqariq: A Multilingual Speech Corpus of Native Languages of Peru forSpeech Recognition","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"listra-automatic-speech-translation-english-1","title":"LiSTra Automatic Speech Translation: English to Lingala Case Study","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mesures-linguistiques-automatiques-pour","title":"Mesures linguistiques automatiques pour l’évaluation des systèmes de Reconnaissance Automatique de la Parole (Automated linguistic measures for automatic speech recognition systems’ evaluation)","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-transfer-learning-for-children","title":"Multilingual Transfer Learning for Children Automatic Speech Recognition","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parlamentparla-a-speech-corpus-of-catalan","title":"ParlamentParla: A Speech Corpus of Catalan Parliamentary Sessions","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parlaspeech-hr-a-freely-available-asr-dataset","title":"ParlaSpeech-HR - a Freely Available ASR Dataset for Croatian Bootstrapped from the ParlaMint Corpus","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"post-stroke-speech-transcription-challenge","title":"Post-Stroke Speech Transcription Challenge (Task B): Correctness Detection in Anomia Diagnosis with Imperfect Transcripts","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"progress-in-multilingual-speech-recognition","title":"Progress in Multilingual Speech Recognition for Low Resource Languages Kurmanji Kurdish, Cree and Inuktut","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"samromur-children-an-icelandic-speech-corpus","title":"Samrómur Children: An Icelandic Speech Corpus","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"snow-mountain-dataset-of-audio-recordings-of","title":"Snow Mountain: Dataset of Audio Recordings of The Bible in Low Resource Languages","date":"2022-06-01","arxiv_id":"2206.01205","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-unified-asr-system-for-the-armenian","title":"Towards a Unified ASR System for the Armenian Standards","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-an-open-source-dutch-speech","title":"Towards an Open-Source Dutch Speech Recognition System for the Healthcare Domain","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-synthesis-based-data-augmentation","title":"Adversarial synthesis based data-augmentation for code-switched spoken language identification","date":"2022-05-30","arxiv_id":"2205.15747","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-activation-network-for-low-resource","title":"Adaptive Activation Network For Low Resource Multilingual Speech Recognition","date":"2022-05-28","arxiv_id":"2205.14326","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-to-articulatory-speech-inversion-1","title":"Acoustic-to-articulatory Speech Inversion with Multi-task Learning","date":"2022-05-27","arxiv_id":"2205.13755","repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-restoration-in-spanish-customer","title":"Punctuation Restoration in Spanish Customer Support Transcripts using Transfer Learning","date":"2022-05-27","arxiv_id":"2205.13961","repositories_listed":0,"syntology":null},{"url":null,"slug":"clinical-dialogue-transcription-error","title":"Clinical Dialogue Transcription Error Correction using Seq2Seq Models","date":"2022-05-26","arxiv_id":"2205.13572","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-adapters-for-personalized-speech","title":"Contextual Adapters for Personalized Speech Recognition in Neural Transducers","date":"2022-05-26","arxiv_id":"2205.13660","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-training-of-speech-enhancement-and-self","title":"Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR","date":"2022-05-26","arxiv_id":"2205.13293","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-investigation-on-applying-acoustic-feature","title":"An Investigation on Applying Acoustic Feature Conversion to ASR of Adult and Child Speech","date":"2022-05-25","arxiv_id":"2205.12477","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-reservoir-computing-models-for","title":"Heterogeneous Reservoir Computing Models for Persian Speech Recognition","date":"2022-05-25","arxiv_id":"2205.12594","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-ctc-based-asr-models-with-gated","title":"Improving CTC-based ASR Models with Gated Interlayer Collaboration","date":"2022-05-25","arxiv_id":"2205.12462","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-lexical-replacements-for-arabic","title":"Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation","date":"2022-05-25","arxiv_id":"2205.12649","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-building-spoken-language-understanding","title":"On Building Spoken Language Understanding Systems for Low Resourced Languages","date":"2022-05-25","arxiv_id":"2205.12818","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-level-modeling-units-for-end-to-end","title":"Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition","date":"2022-05-24","arxiv_id":"2205.11998","repositories_listed":0,"syntology":null},{"url":null,"slug":"calibrate-and-refine-a-novel-and-agile","title":"Calibrate and Refine! A Novel and Agile Framework for ASR-error Robust Intent Detection","date":"2022-05-23","arxiv_id":"2205.11008","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-speech-representation","title":"Self-Supervised Speech Representation Learning: A Review","date":"2022-05-21","arxiv_id":"2205.10643","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-spoken-language-identification-1","title":"Automatic Spoken Language Identification using a Time-Delay Neural Network","date":"2022-05-19","arxiv_id":"2205.09564","repositories_listed":0,"syntology":null},{"url":null,"slug":"insights-on-neural-representations-for-end-to","title":"Insights on Neural Representations for End-to-End Speech Recognition","date":"2022-05-19","arxiv_id":"2205.09456","repositories_listed":0,"syntology":null},{"url":null,"slug":"deploying-self-supervised-learning-in-the","title":"Deploying self-supervised learning in the wild for hybrid automatic speech recognition","date":"2022-05-17","arxiv_id":"2205.08598","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-noise-context-aware-enhancement-for","title":"Streaming Noise Context Aware Enhancement For Automatic Speech Recognition in Multi-Talker Environments","date":"2022-05-17","arxiv_id":"2205.08555","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-consistency-training-for-semi","title":"Improved Consistency Training for Semi-Supervised Sequence-to-Sequence ASR via Speech Chain Reconstruction and Self-Transcribing","date":"2022-05-14","arxiv_id":"2205.06963","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-approaches-for-spoken-language","title":"Pretraining Approaches for Spoken Language Recognition: TalTech Submission to the OLR 2021 Challenge","date":"2022-05-14","arxiv_id":"2205.07083","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-adversarial-data-augmentation","title":"Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition","date":"2022-05-13","arxiv_id":"2205.06445","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-modeling-of-multi-domain-multi-device","title":"Unified Modeling of Multi-Domain Multi-Device ASR Systems","date":"2022-05-13","arxiv_id":"2205.06655","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-audio-visual-multi-person","title":"A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection","date":"2022-05-11","arxiv_id":"2205.05684","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-multi-person-audio-visual","title":"End-to-End Multi-Person Audio/Visual Automatic Speech Recognition","date":"2022-05-11","arxiv_id":"2205.05586","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-of-both-worlds-multi-task-audio-visual","title":"Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection","date":"2022-05-10","arxiv_id":"2205.05206","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-reinforcement-using-target-source","title":"Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition","date":"2022-05-09","arxiv_id":"2205.04433","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-conformer-based-waveform-domain-neural","title":"A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy","date":"2022-05-06","arxiv_id":"2205.03481","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-trac-consortium-systems-for-the-iwslt-2022","title":"ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks","date":"2022-05-04","arxiv_id":"2205.01987","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-meeting-transcription-system-for-an-ad-hoc","title":"A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network","date":"2022-05-02","arxiv_id":"2205.00944","repositories_listed":0,"syntology":null},{"url":null,"slug":"bilingual-end-to-end-asr-with-byte-level","title":"Bilingual End-to-End ASR with Byte-Level Subwords","date":"2022-05-01","arxiv_id":"2205.00485","repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-on-asr-measurement-introducing-the","title":"Discourse on ASR Measurement: Introducing the ARPOCA Assessment Tool","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-documentation-of-hupa-with","title":"Enhancing Documentation of Hupa with Automatic Speech Recognition","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-shared-task-on-speech","title":"Findings of the Shared Task on Speech Recognition for Vulnerable Individuals in Tamil","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-pre-trained-models-for-automatic","title":"Fine-tuning pre-trained models for Automatic Speech Recognition, experiments on a fieldwork corpus of Japhug (Trans-Himalayan family)","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"1ac5b9d8fdb68227535ae9c151c9432c6a8972d7257dc9460f726731f43a0b13","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}