{"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-1/papers/48","list_of":"/task/speech-recognition-1","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":48,"pages_in_order":58,"rows_per_page":100,"rows":[4701,4800],"of":5715,"counts":{"archive_papers_tagged":5715,"with_a_code_link":1277,"where_syntology_ran_a_sample":162,"not_listed_spam_title":0,"listed":5715,"listed_where_code_ran":162,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":134,"every_run_a_failure_of_syntologys_instrument":28,"listed_with_a_run_with_no_instrument_failure":134,"listed_every_run_a_failure_of_syntologys_instrument":28,"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-1","prev":"/task/speech-recognition-1/papers/47","next":"/task/speech-recognition-1/papers/49","papers":[{"url":null,"slug":"neural-text-normalization-with-subword-units","title":"Neural Text Normalization with Subword Units","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-the-bottleneck-in-traditional","title":"Overcoming the bottleneck in traditional assessments of verbal memory: Modeling human ratings and classifying clinical group membership","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tan-jiu-duan-dui-duan-hun-he-mo-xing-jia-gou","title":"探究端對端混合模型架構於華語語音辨識 (An Investigation of Hybrid CTC-Attention Modeling in Mandarin Speech Recognition)","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-and-evaluation-of-a-real-room","title":"Building and Evaluation of a Real Room Impulse Response Dataset","date":"2019-05-30","arxiv_id":"1811.06795","repositories_listed":0,"syntology":null},{"url":null,"slug":"lattice-based-lightly-supervised-acoustic","title":"Lattice-based lightly-supervised acoustic model training","date":"2019-05-30","arxiv_id":"1905.13150","repositories_listed":0,"syntology":null},{"url":null,"slug":"190601496","title":"Regularization Advantages of Multilingual Neural Language Models for Low Resource Domains","date":"2019-05-29","arxiv_id":"1906.01496","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-bfloat16-for-deep-learning","title":"A Study of BFLOAT16 for Deep Learning Training","date":"2019-05-29","arxiv_id":"1905.12322","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-full-connectivity-in-recurrent","title":"Rethinking Full Connectivity in Recurrent Neural Networks","date":"2019-05-29","arxiv_id":"1905.12340","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-with-hybrid-bio-hardware-neural","title":"Inference with Hybrid Bio-hardware Neural Networks","date":"2019-05-28","arxiv_id":"1905.11594","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-emergent-geometry-in-speech-models","title":"Probing emergent geometry in speech models via replica theory","date":"2019-05-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-collaborative-filtering-model-with","title":"A collaborative filtering model with heterogeneous neural networks for recommender systems","date":"2019-05-27","arxiv_id":"1905.11133","repositories_listed":0,"syntology":null},{"url":null,"slug":"ntp-a-neural-network-topology-profiler","title":"NTP : A Neural Network Topology Profiler","date":"2019-05-22","arxiv_id":"1905.09063","repositories_listed":0,"syntology":null},{"url":null,"slug":"190600748","title":"Improving Minimal Gated Unit for Sequential Data","date":"2019-05-21","arxiv_id":"1906.00748","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-to-word-models-with-conversational","title":"Acoustic-to-Word Models with Conversational Context Information","date":"2019-05-21","arxiv_id":"1905.08796","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-speech-separation","title":"A comprehensive study of speech separation: spectrogram vs waveform separation","date":"2019-05-17","arxiv_id":"1905.07497","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-adaptation-with-backpropagation","title":"End-to-end Adaptation with Backpropagation through WFST for On-device Speech Recognition System","date":"2019-05-17","arxiv_id":"1905.07149","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulatory-and-bottleneck-features-for","title":"Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech","date":"2019-05-16","arxiv_id":"1905.06533","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-sentence-scoring-method-using","title":"Effective Sentence Scoring Method using Bidirectional Language Model for Speech Recognition","date":"2019-05-16","arxiv_id":"1905.06655","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-independent-speech-driven-visual","title":"Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models","date":"2019-05-15","arxiv_id":"1905.06860","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-algonauts-project-a-platform-for","title":"The Algonauts Project: A Platform for Communication between the Sciences of Biological and Artificial Intelligence","date":"2019-05-14","arxiv_id":"1905.05675","repositories_listed":0,"syntology":null},{"url":null,"slug":"almost-unsupervised-text-to-speech-and","title":"Almost Unsupervised Text to Speech and Automatic Speech Recognition","date":"2019-05-13","arxiv_id":"1905.06791","repositories_listed":0,"syntology":null},{"url":null,"slug":"encrypted-speech-recognition-using-deep","title":"Encrypted Speech Recognition using Deep Polynomial Networks","date":"2019-05-11","arxiv_id":"1905.05605","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-contrastive-learning-based-deep","title":"Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification","date":"2019-05-11","arxiv_id":"1905.04554","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-with-deep-transformers","title":"Language Modeling with Deep Transformers","date":"2019-05-10","arxiv_id":"1905.04226","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobivsr-a-visual-speech-recognition-solution","title":"MobiVSR: A Visual Speech Recognition Solution for Mobile Devices","date":"2019-05-10","arxiv_id":"1905.03968","repositories_listed":0,"syntology":null},{"url":null,"slug":"190503500","title":"Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech","date":"2019-05-09","arxiv_id":"1905.03500","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-adversarial-perturbations-for","title":"Universal Adversarial Perturbations for Speech Recognition Systems","date":"2019-05-09","arxiv_id":"1905.03828","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hardware-oriented-and-memory-efficient","title":"A Hardware-Oriented and Memory-Efficient Method for CTC Decoding","date":"2019-05-08","arxiv_id":"1905.03175","repositories_listed":0,"syntology":null},{"url":null,"slug":"meeting-transcription-using-virtual","title":"Meeting Transcription Using Virtual Microphone Arrays","date":"2019-05-03","arxiv_id":"1905.02545","repositories_listed":0,"syntology":null},{"url":null,"slug":"parity-models-a-general-framework-for-coding","title":"Parity Models: A General Framework for Coding-Based Resilience in ML Inference","date":"2019-05-02","arxiv_id":"1905.00863","repositories_listed":0,"syntology":null},{"url":null,"slug":"curvature-a-signature-for-action-recognition","title":"Curvature: A signature for Action Recognition in Video Sequences","date":"2019-04-30","arxiv_id":"1904.13003","repositories_listed":0,"syntology":null},{"url":null,"slug":"english-broadcast-news-speech-recognition-by","title":"English Broadcast News Speech Recognition by Humans and Machines","date":"2019-04-30","arxiv_id":"1904.13258","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-sequence-to-sequence-asr","slug":"self-supervised-sequence-to-sequence-asr","title":"Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text","date":"2019-04-30","arxiv_id":"1905.01152","repositories_listed":0,"syntology":null},{"url":null,"slug":"very-deep-self-attention-networks-for-end-to","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","date":"2019-04-30","arxiv_id":"1904.13377","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-speaker-adaptation","title":"Adversarial Speaker Adaptation","date":"2019-04-29","arxiv_id":"1904.12407","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentive-adversarial-learning-for-domain","title":"Attentive Adversarial Learning for Domain-Invariant Training","date":"2019-04-28","arxiv_id":"1904.12400","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-domain-multi-channel-acoustic","title":"Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition","date":"2019-04-28","arxiv_id":"1903.05299","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-geometry-spatial-acoustic-modeling-for","title":"Multi-Geometry Spatial Acoustic Modeling for Distant Speech Recognition","date":"2019-04-28","arxiv_id":"1903.06539","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-tolerance-of-neural-machine","title":"Assessing the Tolerance of Neural Machine Translation Systems Against Speech Recognition Errors","date":"2019-04-24","arxiv_id":"1904.10997","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-interactions-in-autonomous","title":"Natural Language Interactions in Autonomous Vehicles: Intent Detection and Slot Filling from Passenger Utterances","date":"2019-04-23","arxiv_id":"1904.10500","repositories_listed":0,"syntology":null},{"url":null,"slug":"nlp-driven-ensemble-based-automatic-subtitle","title":"NLP Driven Ensemble Based Automatic Subtitle Generation and Semantic Video Summarization Technique","date":"2019-04-22","arxiv_id":"1904.09740","repositories_listed":0,"syntology":null},{"url":null,"slug":"190501974","title":"A Novel Task-Oriented Text Corpus in Silent Speech Recognition and its Natural Language Generation Construction Method","date":"2019-04-19","arxiv_id":"1905.01974","repositories_listed":0,"syntology":null},{"url":null,"slug":"dry-focus-and-transcribe-end-to-end","title":"An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions","date":"2019-04-19","arxiv_id":"1904.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"tts-skins-speaker-conversion-via-asr","title":"TTS Skins: Speaker Conversion via ASR","date":"2019-04-18","arxiv_id":"1904.08983","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-task-learning-framework-for","title":"A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition","date":"2019-04-17","arxiv_id":"1904.08039","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-translation-with-knowledge","title":"End-to-End Speech Translation with Knowledge Distillation","date":"2019-04-17","arxiv_id":"1904.08075","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-ctc-posterior-spike-timings-for","title":"Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation","date":"2019-04-17","arxiv_id":"1904.08311","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-sample-mining-for-the-improved","title":"Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition","date":"2019-04-17","arxiv_id":"1904.08031","repositories_listed":0,"syntology":null},{"url":null,"slug":"hark-side-of-deep-learning-from-grad-student","title":"HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning","date":"2019-04-16","arxiv_id":"1904.07633","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-passing-models-for-robust-and-data","title":"Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation","date":"2019-04-15","arxiv_id":"1904.07209","repositories_listed":0,"syntology":null},{"url":null,"slug":"speechyolo-detection-and-localization-of","title":"SpeechYOLO: Detection and Localization of Speech Objects","date":"2019-04-14","arxiv_id":"1904.07704","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-latency-speaker-independent-continuous","title":"Low-Latency Speaker-Independent Continuous Speech Separation","date":"2019-04-13","arxiv_id":"1904.06478","repositories_listed":0,"syntology":null},{"url":null,"slug":"stc-speaker-recognition-systems-for-the","title":"STC Speaker Recognition Systems for the VOiCES From a Distance Challenge","date":"2019-04-12","arxiv_id":"1904.06093","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-deep-learning-strategies-for","title":"Distributed Deep Learning Strategies For Automatic Speech Recognition","date":"2019-04-10","arxiv_id":"1904.04956","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-semi-supervised-to-almost-unsupervised","title":"From Semi-supervised to Almost-unsupervised Speech Recognition with Very-low Resource by Jointly Learning Phonetic Structures from Audio and Text Embeddings","date":"2019-04-10","arxiv_id":"1904.05078","repositories_listed":0,"syntology":null},{"url":null,"slug":"190409233","title":"Deep Cytometry: Deep learning with Real-time Inference in Cell Sorting and Flow Cytometry","date":"2019-04-09","arxiv_id":"1904.09233","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-monitoring-for-end-to-end-speech","title":"Performance Monitoring for End-to-End Speech Recognition","date":"2019-04-09","arxiv_id":"1904.04896","repositories_listed":0,"syntology":null},{"url":null,"slug":"who-needs-words-lexicon-free-speech","title":"Who Needs Words? Lexicon-Free Speech Recognition","date":"2019-04-09","arxiv_id":"1904.04479","repositories_listed":0,"syntology":null},{"url":null,"slug":"completely-unsupervised-phoneme-recognition-1","title":"Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models","date":"2019-04-08","arxiv_id":"1904.04100","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-output-embeddings-for-end-to-end","title":"Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data","date":"2019-04-08","arxiv_id":"1904.03802","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-methods-for-the-automatic-detection","title":"Exploring Methods for the Automatic Detection of Errors in Manual Transcription","date":"2019-04-08","arxiv_id":"1904.04294","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-recurrent-neural","title":"Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization","date":"2019-04-08","arxiv_id":"1904.04163","repositories_listed":0,"syntology":null},{"url":null,"slug":"speak-your-mind-towards-imagined-speech","title":"SPEAK YOUR MIND! Towards Imagined Speech Recognition With Hierarchical Deep Learning","date":"2019-04-08","arxiv_id":"1904.05746","repositories_listed":0,"syntology":null},{"url":"/paper/token-level-ensemble-distillation-for","slug":"token-level-ensemble-distillation-for","title":"Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion","date":"2019-04-06","arxiv_id":"1904.03446","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-speech-recognition-with","title":"Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions","date":"2019-04-04","arxiv_id":"1904.02619","repositories_listed":0,"syntology":null},{"url":null,"slug":"massively-multilingual-adversarial-speech","title":"Massively Multilingual Adversarial Speech Recognition","date":"2019-04-03","arxiv_id":"1904.02210","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-visual-speech-recognition-for","title":"End-to-End Visual Speech Recognition for Small-Scale Datasets","date":"2019-04-02","arxiv_id":"1904.01954","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-asr-on-alzheimers-disease-detection","title":"Impact of ASR on Alzheimer's Disease Detection: All Errors are Equal, but Deletions are More Equal than Others","date":"2019-04-02","arxiv_id":"1904.01684","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-training-of-neural-mask-based","title":"Unsupervised training of neural mask-based beamforming","date":"2019-04-02","arxiv_id":"1904.01578","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-shared-encoding-representation-for","title":"Learning Shared Encoding Representation for End-to-End Speech Recognition Models","date":"2019-03-31","arxiv_id":"1904.02147","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustically-grounded-word-embeddings-for","title":"Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition","date":"2019-03-29","arxiv_id":"1903.12306","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-acoustic-prosodic-cues-for-word","title":"Modeling Acoustic-Prosodic Cues for Word Importance Prediction in Spoken Dialogues","date":"2019-03-28","arxiv_id":"1903.12238","repositories_listed":0,"syntology":null},{"url":null,"slug":"wasserstein-dependency-measure-for","title":"Wasserstein Dependency Measure for Representation Learning","date":"2019-03-28","arxiv_id":"1903.11780","repositories_listed":0,"syntology":null},{"url":null,"slug":"190410045","title":"Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognition","date":"2019-03-27","arxiv_id":"1904.10045","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speech-enhancement-based-on","title":"Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition","date":"2019-03-22","arxiv_id":"1903.09341","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-de-identification-a-new-entity","title":"Audio De-identification: A New Entity Recognition Task","date":"2019-03-17","arxiv_id":"1903.07037","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-assessment-of-spoken-language","title":"Automatic assessment of spoken language proficiency of non-native children","date":"2019-03-15","arxiv_id":"1903.06409","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-method-for-developing-part-of","title":"Bootstrapping Method for Developing Part-of-Speech Tagged Corpus in Low Resource Languages Tagset - A Focus on an African Igbo","date":"2019-03-12","arxiv_id":"1903.05225","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-minibatch-stochastic-gradient-1","title":"Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling","date":"2019-03-11","arxiv_id":"1903.04192","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-between-monaural-speech","title":"Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling","date":"2019-03-11","arxiv_id":"1903.04567","repositories_listed":0,"syntology":null},{"url":null,"slug":"singing-voice-conversion-with-non-parallel","title":"Singing voice conversion with non-parallel data","date":"2019-03-11","arxiv_id":"1903.04124","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-virtual-doctor-an-interactive-artificial","title":"The Virtual Doctor: An Interactive Artificial Intelligence based on Deep Learning for Non-Invasive Prediction of Diabetes","date":"2019-03-09","arxiv_id":"1903.12069","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-and-semi-supervised-learning-in-asr","title":"Active and Semi-Supervised Learning in ASR: Benefits on the Acoustic and Language Models","date":"2019-03-07","arxiv_id":"1903.02852","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-with-no-speech-or-with","title":"Speech Recognition with no speech or with noisy speech","date":"2019-03-02","arxiv_id":"1903.00739","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-neural-based-dialog-act","title":"Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions","date":"2019-02-28","arxiv_id":"1902.11060","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-end-to-end-speech-recognition","title":"Incorporating End-to-End Speech Recognition Models for Sentiment Analysis","date":"2019-02-28","arxiv_id":"1902.11245","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-neural-online-source-separation-counting","title":"All-neural online source separation, counting, and diarization for meeting analysis","date":"2019-02-21","arxiv_id":"1902.07881","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-nigens-general-sound-events-database","title":"The NIGENS General Sound Events Database","date":"2019-02-21","arxiv_id":"1902.08314","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-with-inadequate-and-incorrect","title":"Learning with Inadequate and Incorrect Supervision","date":"2019-02-20","arxiv_id":"1902.07429","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-spelling-correction-model-for-end-to-end","title":"A spelling correction model for end-to-end speech recognition","date":"2019-02-19","arxiv_id":"1902.07178","repositories_listed":0,"syntology":null},{"url":null,"slug":"learned-in-speech-recognition-contextual","title":"Learned In Speech Recognition: Contextual Acoustic Word Embeddings","date":"2019-02-18","arxiv_id":"1902.06833","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-attention-aligner-a-latency-control-end","title":"Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hopping","date":"2019-02-18","arxiv_id":"1902.06450","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-robot-speech-recognition-using","title":"Enhanced Robot Speech Recognition Using Biomimetic Binaural Sound Source Localization","date":"2019-02-13","arxiv_id":"1902.05446","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-adversarial-attacks-and-defenses","title":"Towards a Robust Deep Neural Network in Texts: A Survey","date":"2019-02-12","arxiv_id":"1902.07285","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-and-face-recognition-the-state","title":"Deep learning and face recognition: the state of the art","date":"2019-02-10","arxiv_id":"1902.03524","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-anchored-speech-recognition","title":"End-to-end Anchored Speech Recognition","date":"2019-02-06","arxiv_id":"1902.02383","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-multi-task-learning-to-improve-the","title":"Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models","date":"2019-02-02","arxiv_id":"1902.01951","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-guided-symbiotic-training-for","title":"Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM","date":"2019-01-30","arxiv_id":"1901.10997","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-convolutional-neural-network-model-based-on","title":"A Convolutional Neural Network model based on Neutrosophy for Noisy Speech Recognition","date":"2019-01-27","arxiv_id":"1901.10629","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovery-of-important-subsequences-in","title":"Discovery of Important Subsequences in Electrocardiogram Beats Using the Nearest Neighbour Algorithm","date":"2019-01-26","arxiv_id":"1901.09187","repositories_listed":0,"syntology":null}],"record_sha256":"4a1ec4a6b7e7ed09a2f93f02a183a31a511c821b6d9f2c7d9ec98c194ba4bd28","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}