{"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/24","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":24,"pages_in_order":31,"rows_per_page":100,"rows":[2301,2400],"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/23","next":"/task/automatic-speech-recognition/papers/25","papers":[{"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},{"url":null,"slug":"fully-convolutional-asr-for-less-resourced","title":"Fully Convolutional ASR for Less-Resourced Endangered Languages","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-language-model-for-low-resource","title":"Improving the Language Model for Low-Resource ASR with Online Text Corpora","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-corpus-of-czech-parliament-plenary","title":"Large Corpus of Czech Parliament Plenary Hearings","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-vocabulary-read-speech-corpora-for-four","title":"Large Vocabulary Read Speech Corpora for Four Ethiopian Languages: Amharic, Tigrigna, Oromo and Wolaytta","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linto-platform-a-smart-open-voice-assistant","title":"LinTO Platform: A Smart Open Voice Assistant for Business Environments","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"malayalam-speech-corpus-design-and","title":"Malayalam Speech Corpus: Design and Development for Dravidian Language","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-staged-cross-lingual-acoustic-model","title":"Multi-Staged Cross-Lingual Acoustic Model Adaption for Robust Speech Recognition in Real-World Applications - A Case Study on German Oral History Interviews","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-construction-of-the-asr-oriented-indian","title":"On Construction of the ASR-oriented Indian English Pronunciation Dictionary","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/open-source-high-quality-speech-datasets-for","slug":"open-source-high-quality-speech-datasets-for","title":"Open-Source High Quality Speech Datasets for Basque, Catalan and Galician","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-corpus-for-japanese-spoken-to","title":"Parallel Corpus for Japanese Spoken-to-Written Style Conversion","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phonemic-transcription-of-low-resource","title":"Phonemic Transcription of Low-Resource Languages: To What Extent can Preprocessing be Automated?","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"preparation-of-bangla-speech-corpus-from","title":"Preparation of Bangla Speech Corpus from Publicly Available Audio \\& Text","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rsc-a-romanian-read-speech-corpus-for","title":"RSC: A Romanian Read Speech Corpus for Automatic Speech Recognition","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"samr-omur-crowd-sourcing-data-collection-for","title":"Samr\\'omur: Crowd-sourcing Data Collection for Icelandic Speech Recognition","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-safe-t-corpus-a-new-resource-for","title":"The SAFE-T Corpus: A New Resource for Simulated Public Safety Communications","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-building-an-automatic-transcription","title":"Towards Building an Automatic Transcription System for Language Documentation: Experiences from Muyu","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-less-resourced-semitic","title":"Transfer Learning for Less-Resourced Semitic Languages Speech Recognition: the Case of Amharic","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-automatic-speech-recognition-in-spoken","title":"Using Automatic Speech Recognition in Spoken Corpus Curation","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"where-are-we-in-named-entity-recognition-from","title":"Where are we in Named Entity Recognition from Speech?","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multiresolution-and-multimodal-speech","title":"Multiresolution and Multimodal Speech Recognition with Transformers","date":"2020-04-29","arxiv_id":"2004.14840","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-trained-transformers-models-for","title":"Jointly Trained Transformers models for Spoken Language Translation","date":"2020-04-25","arxiv_id":"2004.12111","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-to-dialog-act-recognition","title":"End-to-end speech-to-dialog-act recognition","date":"2020-04-23","arxiv_id":"2004.11419","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-non-autoregressive-model-for","title":"A Study of Non-autoregressive Model for Sequence Generation","date":"2020-04-22","arxiv_id":"2004.10454","repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-prediction-in-spontaneous","title":"Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?","date":"2020-04-13","arxiv_id":"2004.05985","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-diarization-with-lexical-information-1","title":"Speaker Diarization with Lexical Information","date":"2020-04-13","arxiv_id":"2004.06756","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-readability-for-automatic-speech","title":"Improving Readability for Automatic Speech Recognition Transcription","date":"2020-04-09","arxiv_id":"2004.04438","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-modelling-for-five","title":"Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech","date":"2020-04-08","arxiv_id":"2004.06480","repositories_listed":0,"syntology":null},{"url":null,"slug":"homophone-based-label-smoothing-in-end-to-end","title":"Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition","date":"2020-04-07","arxiv_id":"2004.03437","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-speech-adversarial-examples","title":"Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement","date":"2020-03-31","arxiv_id":"2003.13917","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-latency-asr-for-simultaneous-speech","title":"Low Latency ASR for Simultaneous Speech Translation","date":"2020-03-22","arxiv_id":"2003.09891","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-for-speech-recognition-on","title":"Training for Speech Recognition on Coprocessors","date":"2020-03-22","arxiv_id":"2003.12366","repositories_listed":0,"syntology":null},{"url":null,"slug":"deliberation-model-based-two-pass-end-to-end","title":"Deliberation Model Based Two-Pass End-to-End Speech Recognition","date":"2020-03-17","arxiv_id":"2003.07962","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-accuracy-and-low-latency-speech","title":"High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model","date":"2020-03-17","arxiv_id":"2003.07482","repositories_listed":0,"syntology":null},{"url":null,"slug":"asr-error-correction-and-domain-adaptation","title":"ASR Error Correction and Domain Adaptation Using Machine Translation","date":"2020-03-13","arxiv_id":"2003.07692","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-autoregressive-transducer-hat","title":"Hybrid Autoregressive Transducer (hat)","date":"2020-03-12","arxiv_id":"2003.07705","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-networks-for-automatic-speech","title":"Deep Neural Networks for Automatic Speech Processing: A Survey from Large Corpora to Limited Data","date":"2020-03-09","arxiv_id":"2003.04241","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-noise-robust-automatic-speech","title":"Improving noise robust automatic speech recognition with single-channel time-domain enhancement network","date":"2020-03-09","arxiv_id":"2003.03998","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-time-delay-transformer-for-real","title":"Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection","date":"2020-03-03","arxiv_id":"2003.01309","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-uyghur-asr-systems-with-decoders","title":"Improving Uyghur ASR systems with decoders using morpheme-based language models","date":"2020-03-03","arxiv_id":"2003.01509","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-density-ratio-approach-to-language-model","title":"A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition","date":"2020-02-26","arxiv_id":"2002.11268","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-training-of-deep-neural-network","title":"Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition","date":"2020-02-24","arxiv_id":"2002.10502","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-asr-with-lightweight-and","title":"Attention-based ASR with Lightweight and Dynamic Convolutions","date":"2020-02-20","arxiv_id":"1912.11793","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-adjusted-neuron-activation-profiles","title":"Gradient-Adjusted Neuron Activation Profiles for Comprehensive Introspection of Convolutional Speech Recognition Models","date":"2020-02-19","arxiv_id":"2002.08125","repositories_listed":0,"syntology":null},{"url":null,"slug":"rtmobile-beyond-real-time-mobile-acceleration","title":"RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition","date":"2020-02-19","arxiv_id":"2002.11474","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-corpus-of-ainu-folklore-and-end-to-end","title":"Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language","date":"2020-02-16","arxiv_id":"2002.06675","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speaker-adaptation-using","title":"Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR","date":"2020-02-14","arxiv_id":"2002.06165","repositories_listed":0,"syntology":null},{"url":null,"slug":"looking-enhances-listening-recovering-missing","title":"Looking Enhances Listening: Recovering Missing Speech Using Images","date":"2020-02-13","arxiv_id":"2002.05639","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-diverse-and-natural-text-to-speech","title":"Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior","date":"2020-02-06","arxiv_id":"2002.03788","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-multi-channel-speech-recognition-using","title":"Robust Multi-channel Speech Recognition using Frequency Aligned Network","date":"2020-02-06","arxiv_id":"2002.02520","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-mind-reading","title":"Continuous Silent Speech Recognition using EEG","date":"2020-02-06","arxiv_id":"2002.03851","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-automatic-speech-recognition","title":"End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection","date":"2020-02-03","arxiv_id":"2002.00551","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogue-based-simulation-for-cultural","title":"Dialogue-Based Simulation For Cultural Awareness Training","date":"2020-02-01","arxiv_id":"2002.00223","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-learnable-front-end-for-multi-channel","title":"Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning","date":"2020-02-01","arxiv_id":"2002.00125","repositories_listed":0,"syntology":null},{"url":null,"slug":"but-opensat-2019-speech-recognition-system","title":"BUT Opensat 2019 Speech Recognition System","date":"2020-01-30","arxiv_id":"2001.11360","repositories_listed":0,"syntology":null},{"url":null,"slug":"environment-aware-reconfigurable-noise","title":"Environment-aware Reconfigurable Noise Suppression","date":"2020-01-29","arxiv_id":"2001.10718","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-contextual-modeling-for-asr-correction","title":"Joint Contextual Modeling for ASR Correction and Language Understanding","date":"2020-01-28","arxiv_id":"2002.00750","repositories_listed":0,"syntology":null},{"url":null,"slug":"lattice-based-improvements-for-voice","title":"Lattice-based Improvements for Voice Triggering Using Graph Neural Networks","date":"2020-01-25","arxiv_id":"2001.10822","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-gradient-approximation-for-memory","title":"Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Network","date":"2020-01-24","arxiv_id":"2001.08885","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-asr-by-end-to-end-self","title":"Semi-supervised ASR by End-to-end Self-training","date":"2020-01-24","arxiv_id":"2001.09128","repositories_listed":0,"syntology":null},{"url":null,"slug":"tlt-school-a-corpus-of-non-native-children","title":"TLT-school: a Corpus of Non Native Children Speech","date":"2020-01-22","arxiv_id":"2001.08051","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-online-ctcattention-end-to","title":"Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture","date":"2020-01-15","arxiv_id":"2001.08290","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-spoken-language-understanding-by","title":"Improving Spoken Language Understanding By Exploiting ASR N-best Hypotheses","date":"2020-01-11","arxiv_id":"2001.05284","repositories_listed":0,"syntology":null}],"record_sha256":"dfd699eb2325fc9cc74dcef5e58185cc2a072fc779c9f194c8e9cf871bea3966","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}