{"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/26","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":26,"pages_in_order":32,"rows_per_page":100,"rows":[2501,2600],"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/25","next":"/task/automatic-speech-recognition-2/papers/27","papers":[{"url":null,"slug":"modular-end-to-end-automatic-speech","title":"Modular End-to-end Automatic Speech Recognition Framework for Acoustic-to-word Model","date":"2020-07-31","arxiv_id":"2008.00953","repositories_listed":0,"syntology":null},{"url":null,"slug":"utterance-wise-meeting-transcription-system","title":"Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones","date":"2020-07-31","arxiv_id":"2007.15868","repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-rnn-t-models-surpassing-high","title":"Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability","date":"2020-07-30","arxiv_id":"2007.15188","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-cross-lingual-knowledge-in","title":"Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource Languages","date":"2020-07-29","arxiv_id":"2007.15074","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-kalman-filtering-for-speech","title":"Neural Kalman Filtering for Speech Enhancement","date":"2020-07-28","arxiv_id":"2007.13962","repositories_listed":0,"syntology":null},{"url":null,"slug":"effects-of-language-relatedness-for-cross-1","title":"Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models","date":"2020-07-22","arxiv_id":"2007.11648","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-adversarial-examples-for-robust-hybrid","title":"Audio Adversarial Examples for Robust Hybrid CTC/Attention Speech Recognition","date":"2020-07-21","arxiv_id":"2007.10723","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-search-for-speech","title":"Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks","date":"2020-07-17","arxiv_id":"2007.08818","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-an-automated-soap-note-classifying","title":"Towards an Automated SOAP Note: Classifying Utterances from Medical Conversations","date":"2020-07-17","arxiv_id":"2007.08749","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-faults-in-our-asrs-an-overview-of-attacks","title":"SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems","date":"2020-07-13","arxiv_id":"2007.06622","repositories_listed":0,"syntology":null},{"url":null,"slug":"massively-multilingual-asr-50-languages-1","title":"Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters","date":"2020-07-06","arxiv_id":"2007.03001","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-graph-random-process-for-relational","title":"Deep Graph Random Process for Relational-Thinking-Based Speech Recognition","date":"2020-07-04","arxiv_id":"2007.02126","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-prediction-of-punctuation-and-1","title":"Robust Prediction of Punctuation and Truecasing for Medical ASR","date":"2020-07-04","arxiv_id":"2007.02025","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuni-neural-asr-with-phoneme-level","title":"CUNI Neural ASR with Phoneme-Level Intermediate Step for\\textasciitildeNon-Native\\textasciitildeSLT at IWSLT 2020","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/end-to-end-offline-speech-translation-system","slug":"end-to-end-offline-speech-translation-system","title":"End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"how-accents-confound-probing-for-accent","title":"How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-effect-of-auxiliary","title":"Investigating the effect of auxiliary objectives for the automated grading of learner English speech transcriptions","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-vocabulary-read-speech-corpora-for-four-1","title":"Large Vocabulary Read Speech Corpora for Four Ethiopian Languages: Amharic, Tigrigna, Oromo, and Wolaytta","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-and-multiresolution-speech","title":"Multimodal and Multiresolution Speech Recognition with Transformers","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-neural-machine-translation-with-asr","title":"Robust Neural Machine Translation with ASR Errors","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simulspeech-end-to-end-simultaneous-speech-to","title":"SimulSpeech: End-to-End Simultaneous Speech to Text Translation","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"start-before-end-and-end-to-end-neural-speech","title":"Start-Before-End and End-to-End: Neural Speech Translation by AppTek and RWTH Aachen University","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-afrl-iwslt-2020-systems-work-from-home","title":"The AFRL IWSLT 2020 Systems: Work-From-Home Edition","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tigrinya-automatic-speech-recognition-with","title":"Tigrinya Automatic Speech recognition with Morpheme based recognition units","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-end-2-end-learning-for-predicting","title":"Towards end-2-end learning for predicting behavior codes from spoken utterances in psychotherapy conversations","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-stream-translation-adaptive","title":"Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-asr-error-correction","title":"Towards Understanding ASR Error Correction for Medical Conversations","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-frequency-lstm-an-efficient","title":"Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition","date":"2020-06-30","arxiv_id":"2007.00131","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-machine-translation-for-multilingual","title":"Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversion","date":"2020-06-25","arxiv_id":"2006.14194","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-transformer-asr-with-blockwise","title":"Streaming Transformer ASR with Blockwise Synchronous Inference","date":"2020-06-25","arxiv_id":"2006.14941","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-active-learning-for-automatic","title":"Boosting Active Learning for Speech Recognition with Noisy Pseudo-labeled Samples","date":"2020-06-19","arxiv_id":"2006.11021","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-speaker-counting-speech-recognition-and","title":"Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers","date":"2020-06-19","arxiv_id":"2006.10930","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-code-switching-language-models-for","title":"End-to-End Code Switching Language Models for Automatic Speech Recognition","date":"2020-06-16","arxiv_id":"2006.08870","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-of-acoustic-model-parameters-in","title":"Quantization of Acoustic Model Parameters in Automatic Speech Recognition Framework","date":"2020-06-16","arxiv_id":"2006.09054","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automated-assessment-of-stuttering","title":"Towards Automated Assessment of Stuttering and Stuttering Therapy","date":"2020-06-16","arxiv_id":"2006.09222","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-of-end-to-end-asr-for-openstt","title":"Exploration of End-to-End ASR for OpenSTT -- Russian Open Speech-to-Text Dataset","date":"2020-06-15","arxiv_id":"2006.08274","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-jhu-multi-microphone-multi-speaker-asr","title":"The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge","date":"2020-06-14","arxiv_id":"2006.07898","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-for-training-dialog-models","title":"Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors","date":"2020-06-10","arxiv_id":"2006.05635","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cross-lingual-transfer-learning-for","title":"Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation","date":"2020-06-09","arxiv_id":"2006.05474","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-not-to-discriminate-task-agnostic","title":"Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition","date":"2020-06-09","arxiv_id":"2006.05257","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effectiveness-of-neural-text","title":"On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech","date":"2020-06-09","arxiv_id":"2006.05129","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-rnn-t-for-open-domain-asr","title":"Contextual RNN-T For Open Domain ASR","date":"2020-06-04","arxiv_id":"2006.03411","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-talker-asr-for-an-unknown-number-of","title":"Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR","date":"2020-06-04","arxiv_id":"2006.02786","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-british-sign-language-1","title":"Transfer Learning for British Sign Language Modelling","date":"2020-06-03","arxiv_id":"2006.02144","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-the-quality-and-stability-of-a","title":"Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer","date":"2020-06-02","arxiv_id":"2006.01416","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-audio-attacks-on-asr-systems-with","title":"Detecting Audio Attacks on ASR Systems with Dropout Uncertainty","date":"2020-06-02","arxiv_id":"2006.01906","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilated-u-net-based-approach-for-multichannel","title":"Dilated U-net based approach for multichannel speech enhancement from First-Order Ambisonics recordings","date":"2020-06-02","arxiv_id":"2006.01708","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-effective-contextual-language-modeling","title":"An Effective Contextual Language Modeling Framework for Speech Summarization with Augmented Features","date":"2020-06-01","arxiv_id":"2006.01189","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyse-de-l-effet-de-la-r-everb-eration-sur","title":"Analyse de l'effet de la r\\'everb\\'eration sur la reconnaissance automatique de la parole (Analyzing how reverberation affects Automatic Speech Recognition)","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-variational-autoencoder-for","title":"Constrained Variational Autoencoder for improving EEG based Speech Recognition Systems","date":"2020-06-01","arxiv_id":"2006.02902","repositories_listed":0,"syntology":null},{"url":null,"slug":"introduction-d-informations-s-emantiques-dans","title":"Introduction d'informations s\\'emantiques dans un syst\\`eme de reconnaissance de la parole (Despite spectacular advances in recent years, the Automatic Speech Recognition (ASR) systems still make mistakes, especially in noisy environments)","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-recognize-code-switched-speech","title":"Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition","date":"2020-06-01","arxiv_id":"2006.00782","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconnaissance-automatique-de-la-parole-g-en","title":"Reconnaissance automatique de la parole : g\\'en\\'eration des prononciations non natives pour l'enrichissement du lexique (In this study we propose a method for lexicon adaptation in order to improve the automatic speech recognition (ASR) of non-native speakers)","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sur-l-utilisation-de-la-reconnaissance","title":"Sur l'utilisation de la reconnaissance automatique de la parole pour l'aide au diagnostic diff\\'erentiel entre la maladie de Parkinson et l'AMS (On using automatic speech recognition for the differential diagnosis of Parkinson's Disease and MSA This article presents a study regarding the contribution of automatic speech processing in the differential diagnosis between Parkinson's disease and MSA (Multi-System Atrophies))","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-masking-for-improved-stability-in","title":"Dynamic Masking for Improved Stability in Spoken Language Translation","date":"2020-05-30","arxiv_id":"2006.00249","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-audio-enriched-bert-based-framework-for","title":"An Audio-enriched BERT-based Framework for Spoken Multiple-choice Question Answering","date":"2020-05-25","arxiv_id":"2005.12142","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-mispronunciation-detection","title":"An End-to-End Mispronunciation Detection System for L2 English Speech Leveraging Novel Anti-Phone Modeling","date":"2020-05-25","arxiv_id":"2005.11950","repositories_listed":0,"syntology":null},{"url":"/paper/ft-speech-danish-parliament-speech-corpus","slug":"ft-speech-danish-parliament-speech-corpus","title":"FT Speech: Danish Parliament Speech Corpus","date":"2020-05-25","arxiv_id":"2005.12368","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-evaluation-of-importance-maps-in","title":"Large scale evaluation of importance maps in automatic speech recognition","date":"2020-05-21","arxiv_id":"2005.10929","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-label-synchronous-and-frame","title":"A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition","date":"2020-05-20","arxiv_id":"2005.10113","repositories_listed":0,"syntology":null},{"url":null,"slug":"early-stage-lm-integration-using-local-and","title":"Early Stage LM Integration Using Local and Global Log-Linear Combination","date":"2020-05-20","arxiv_id":"2005.10049","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-large-margin-softmax-in","title":"Investigation of Large-Margin Softmax in Neural Language Modeling","date":"2020-05-20","arxiv_id":"2005.10089","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-proper-noun-recognition-in-end-to","title":"Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion","date":"2020-05-19","arxiv_id":"2005.09756","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-effective-end-to-end-modeling-approach-for","title":"An Effective End-to-End Modeling Approach for Mispronunciation Detection","date":"2020-05-18","arxiv_id":"2005.08440","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-multi-channel-recognition-of","title":"Audio-visual Multi-channel Recognition of Overlapped Speech","date":"2020-05-18","arxiv_id":"2005.08571","repositories_listed":0,"syntology":null},{"url":null,"slug":"weak-attention-suppression-for-transformer","title":"Weak-Attention Suppression For Transformer Based Speech Recognition","date":"2020-05-18","arxiv_id":"2005.09137","repositories_listed":0,"syntology":null},{"url":"/paper/accentdb-a-database-of-non-native-english","slug":"accentdb-a-database-of-non-native-english","title":"AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition","date":"2020-05-16","arxiv_id":"2005.07973","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-sparsity-neural-networks-for","title":"Dynamic Sparsity Neural Networks for Automatic Speech Recognition","date":"2020-05-16","arxiv_id":"2005.10627","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-spelling-inconsistencies-in-code","title":"Reducing Spelling Inconsistencies in Code-Switching ASR using Contextualized CTC Loss","date":"2020-05-16","arxiv_id":"2005.07920","repositories_listed":0,"syntology":null},{"url":null,"slug":"that-sounds-familiar-an-analysis-of-phonetic","title":"That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages","date":"2020-05-16","arxiv_id":"2005.08118","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-dependent-acoustic-modeling-without","title":"Context-Dependent Acoustic Modeling without Explicit Phone Clustering","date":"2020-05-15","arxiv_id":"2005.07578","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextualizing-asr-lattice-rescoring-with","title":"Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model","date":"2020-05-15","arxiv_id":"2005.07394","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-do-not-need-more-data-improving-end-to","title":"You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation","date":"2020-05-14","arxiv_id":"2005.07157","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-estimation-of-inteligibility","title":"Automatic Estimation of Intelligibility Measure for Consonants in Speech","date":"2020-05-12","arxiv_id":"2005.06065","repositories_listed":0,"syntology":null},{"url":null,"slug":"discretalk-text-to-speech-as-a-machine","title":"DiscreTalk: Text-to-Speech as a Machine Translation Problem","date":"2020-05-12","arxiv_id":"2005.05525","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-learning-for-end-to-end-automatic","title":"Incremental Learning for End-to-End Automatic Speech Recognition","date":"2020-05-11","arxiv_id":"2005.04288","repositories_listed":0,"syntology":null},{"url":null,"slug":"rnn-t-models-fail-to-generalize-to-out-of","title":"RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions","date":"2020-05-07","arxiv_id":"2005.03271","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-perceptimatic-english-benchmark-for","title":"The Perceptimatic English Benchmark for Speech Perception Models","date":"2020-05-07","arxiv_id":"2005.03418","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-visual-self-supervision-improve-learning","title":"Does Visual Self-Supervision Improve Learning of Speech Representations for Emotion Recognition?","date":"2020-05-04","arxiv_id":"2005.01400","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-robust-unsupervised-contextual","title":"Fast and Robust Unsupervised Contextual Biasing for Speech Recognition","date":"2020-05-04","arxiv_id":"2005.01677","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiqt-multimodal-learning-for-real-time","title":"MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech","date":"2020-05-02","arxiv_id":"2005.00812","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-clarin-transcription-portal-for-interview","title":"A CLARIN Transcription Portal for Interview Data","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-phonetic-approach-for-asr-of-less","title":"Acoustic-Phonetic Approach for ASR of Less Resourced Languages Using Monolingual and Cross-Lingual Information","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-investigative-study-of-multi-modal-cross","title":"An Investigative Study of Multi-Modal Cross-Lingual Retrieval","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-globalphone-and-ethiopian","title":"Analysis of GlobalPhone and Ethiopian Languages Speech Corpora for Multilingual ASR","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/artie-bias-corpus-an-open-dataset-for","slug":"artie-bias-corpus-an-open-dataset-for","title":"Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arzen-a-speech-corpus-for-code-switched","title":"ArzEn: A Speech Corpus for Code-switched Egyptian Arabic-English","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"atc-anno-semantic-annotation-for-air-traffic","title":"ATC-ANNO: Semantic Annotation for Air Traffic Control with Assistive Auto-Annotation","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-for-uyghur","title":"Automatic Speech Recognition for Uyghur through Multilingual Acoustic Modeling","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-transcription-challenges-for","title":"Automatic Transcription Challenges for Inuktitut, a Low-Resource Polysynthetic Language","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatically-assess-children-s-reading","title":"Automatically Assess Children's Reading Skills","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ceasr-a-corpus-for-evaluating-automatic","title":"CEASR: A Corpus for Evaluating Automatic Speech Recognition","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-of-applying-automatic-speech","title":"Challenges of Applying Automatic Speech Recognition for Transcribing EU Parliament Committee Meetings: A Pilot Study","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"corpora-for-cross-language-information","title":"Corpora for Cross-Language Information Retrieval in Six Less-Resourced Languages","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"corpus-generation-for-voice-command-in-smart","title":"Corpus Generation for Voice Command in Smart Home and the Effect of Speech Synthesis on End-to-End SLU","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"crossing-the-ssh-bridge-with-interview-data","title":"Crossing the SSH Bridge with Interview Data","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dnn-based-multilingual-automatic-speech","title":"DNN-Based Multilingual Automatic Speech Recognition for Wolaytta using Oromo Speech","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-and-improving-child-directed","title":"Evaluating and Improving Child-Directed Automatic Speech Recognition","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-off-the-shelf-speech","title":"Evaluation of Off-the-shelf Speech Recognizers Across Diverse Dialogue Domains","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-pre-training-with-alignments-for","title":"Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition","date":"2020-05-01","arxiv_id":"2005.00572","repositories_listed":0,"syntology":null}],"record_sha256":"46ae520f528ea0a138b1d1142dd77dda3e8e6ad0d272e90c6c0c68e009f5b7e4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}