{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-recognition/papers/45","list_of":"/task/speech-recognition","task":"Speech Recognition","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":45,"pages_in_order":65,"rows_per_page":100,"rows":[4401,4500],"of":6433,"counts":{"archive_papers_tagged":6433,"with_a_code_link":1373,"where_syntology_ran_a_sample":196,"not_listed_spam_title":0,"listed":6433,"listed_where_code_ran":196,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":162,"every_run_a_failure_of_syntologys_instrument":34,"listed_with_a_run_with_no_instrument_failure":162,"listed_every_run_a_failure_of_syntologys_instrument":34,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speech-recognition","prev":"/task/speech-recognition/papers/44","next":"/task/speech-recognition/papers/46","papers":[{"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":"listen-attentively-and-spell-once-whole","title":"Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition","date":"2020-05-11","arxiv_id":"2005.04862","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantitative-analysis-of-image-classification","title":"Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices","date":"2020-05-11","arxiv_id":"2005.04968","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":"clustering-for-graph-datasets-via-gumbel","title":"Community Detection Clustering via Gumbel Softmax","date":"2020-05-05","arxiv_id":"2005.02372","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-whispered-speech-recognition-with","title":"End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Pseudo Whisper Pre-training","date":"2020-05-05","arxiv_id":"2005.01972","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":"off-the-shelf-deep-learning-is-not-enough","title":"Off-the-shelf deep learning is not enough: parsimony, Bayes and causality","date":"2020-05-04","arxiv_id":"2005.01557","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-language-score-based-output-selection","title":"A language score based output selection method for multilingual speech recognition","date":"2020-05-02","arxiv_id":"2005.00851","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":"class-based-lstm-russian-language-model-with","title":"Class-based LSTM Russian Language Model with Linguistic Information","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cobiliro-a-research-platform-for-bimodal","title":"CoBiLiRo: A Research Platform for Bimodal Corpora","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":"development-and-evaluation-of-speech","title":"Development and Evaluation of Speech Synthesis Corpora for Latvian","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":"gender-detection-from-human-voice-using","title":"Gender Detection from Human Voice Using Tensor Analysis","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-speech-recognition-for-the-elderly","title":"Improving Speech Recognition for the Elderly: A New Corpus of Elderly Japanese Speech and Investigation of Acoustic Modeling for Speech Recognition","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-head-monotonic-chunkwise-attention-for","title":"Multi-head Monotonic Chunkwise Attention For Online Speech Recognition","date":"2020-05-01","arxiv_id":"2005.00205","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":"semi-supervised-acoustic-and-language-model-1","title":"Semi-supervised acoustic and language model training for English-isiZulu code-switched speech recognition","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-transcription-challenges-for-resource","title":"Speech Transcription Challenges for Resource Constrained Indigenous Language Cree","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"style-variation-as-a-vantage-point-for-code","title":"Style Variation as a Vantage Point for Code-Switching","date":"2020-05-01","arxiv_id":"2005.00458","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-2019-bbn-cross-lingual-information","title":"The 2019 BBN Cross-lingual Information Retrieval System","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-an-efficient-code-mixed-grapheme-to","title":"Towards an Efficient Code-Mixed Grapheme-to-Phoneme Conversion in an Agglutinative Language: A Case Study on To-Korean Transliteration","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":"learning-to-rank-intents-in-voice-assistants","title":"Learning to Rank Intents in Voice Assistants","date":"2020-04-30","arxiv_id":"2005.00119","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":"adversarial-feature-learning-and-unsupervised","title":"Adversarial Feature Learning and Unsupervised Clustering based Speech Synthesis for Found Data with Acoustic and Textual Noise","date":"2020-04-28","arxiv_id":"2004.13595","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-speech-separation-using-spatially","title":"Neural Speech Separation Using Spatially Distributed Microphones","date":"2020-04-28","arxiv_id":"2004.13670","repositories_listed":0,"syntology":null},{"url":null,"slug":"research-on-modeling-units-of-transformer","title":"Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition","date":"2020-04-26","arxiv_id":"2004.13522","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":"adversarial-machine-learning-in-network","title":"Adversarial Machine Learning in Network Intrusion Detection Systems","date":"2020-04-23","arxiv_id":"2004.11898","repositories_listed":0,"syntology":null},{"url":null,"slug":"cloud-based-face-and-speech-recognition-for","title":"Cloud-Based Face and Speech Recognition for Access Control Applications","date":"2020-04-23","arxiv_id":"2004.11168","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":"curriculum-pre-training-for-end-to-end-speech","title":"Curriculum Pre-training for End-to-End Speech Translation","date":"2020-04-21","arxiv_id":"2004.10093","repositories_listed":0,"syntology":null},{"url":null,"slug":"chime-6-challenge-tackling-multispeaker","title":"CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings","date":"2020-04-20","arxiv_id":"2004.09249","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-agnostic-multilingual-modeling","title":"Language-agnostic Multilingual Modeling","date":"2020-04-20","arxiv_id":"2004.09571","repositories_listed":0,"syntology":null},{"url":null,"slug":"whaletrans-e2e-whisper-to-natural-speech","title":"End-to-End Whisper to Natural Speech Conversion using Modified Transformer Network","date":"2020-04-20","arxiv_id":"2004.09347","repositories_listed":0,"syntology":null},{"url":null,"slug":"allovera-a-multilingual-allophone-database","title":"AlloVera: A Multilingual Allophone Database","date":"2020-04-17","arxiv_id":"2004.08031","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-recognition-in-bengali-language-from","title":"Speaker Recognition in Bengali Language from Nonlinear Features","date":"2020-04-15","arxiv_id":"2004.07820","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-translation-and-the-end-to-end-promise","title":"Speech Translation and the End-to-End Promise: Taking Stock of Where We Are","date":"2020-04-14","arxiv_id":"2004.06358","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":"improved-speech-representations-with-multi","title":"Improved Speech Representations with Multi-Target Autoregressive Predictive Coding","date":"2020-04-11","arxiv_id":"2004.05274","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimum-latency-training-strategies-for","title":"Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR","date":"2020-04-10","arxiv_id":"2004.05009","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":"an-investigation-of-phone-based-subword-units","title":"An investigation of phone-based subword units for end-to-end speech recognition","date":"2020-04-08","arxiv_id":"2004.04290","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":"evaluating-the-communication-efficiency-in","title":"Evaluating the Communication Efficiency in Federated Learning Algorithms","date":"2020-04-06","arxiv_id":"2004.02738","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-and-language-model","title":"Semi-supervised acoustic and language model training for English-isiZulu code-switched speech recognition","date":"2020-04-05","arxiv_id":"2004.04054","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-swiss-german-dictionary-variation-in-speech","title":"A Swiss German Dictionary: Variation in Speech and Writing","date":"2020-03-31","arxiv_id":"2004.00139","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":"serialized-output-training-for-end-to-end","title":"Serialized Output Training for End-to-End Overlapped Speech Recognition","date":"2020-03-28","arxiv_id":"2003.12687","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-you-hear-me-textit-now-sensitive","title":"Can you hear me $\\textit{now}$? Sensitive comparisons of human and machine perception","date":"2020-03-27","arxiv_id":"2003.12362","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-performance-sequence-to-sequence-model","title":"High Performance Sequence-to-Sequence Model for Streaming Speech Recognition","date":"2020-03-22","arxiv_id":"2003.10022","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":"a-joint-approach-to-compound-splitting-and","title":"A Joint Approach to Compound Splitting and Idiomatic Compound Detection","date":"2020-03-21","arxiv_id":"2003.09606","repositories_listed":0,"syntology":null},{"url":null,"slug":"techniques-for-vocabulary-expansion-in-hybrid","title":"Techniques for Vocabulary Expansion in Hybrid Speech Recognition Systems","date":"2020-03-19","arxiv_id":"2003.09024","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}],"record_sha256":"d44273099af2fab80a1bcfaee7eab30fbe5307e6e23ebd35711a1237b567e474","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}