{"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/51","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":51,"pages_in_order":58,"rows_per_page":100,"rows":[5001,5100],"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/50","next":"/task/speech-recognition-1/papers/52","papers":[{"url":null,"slug":"contextual-language-model-adaptation-for","title":"Contextual Language Model Adaptation for Conversational Agents","date":"2018-06-26","arxiv_id":"1806.10215","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-an-overview-1","title":"Deep Reinforcement Learning: An Overview","date":"2018-06-23","arxiv_id":"1806.08894","repositories_listed":0,"syntology":null},{"url":null,"slug":"persistent-hidden-states-and-nonlinear","title":"Persistent Hidden States and Nonlinear Transformation for Long Short-Term Memory","date":"2018-06-22","arxiv_id":"1806.08748","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automated-single-channel-source","title":"Towards Automated Single Channel Source Separation using Neural Networks","date":"2018-06-21","arxiv_id":"1806.08086","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommending-scientific-videos-based-on","title":"Recommending Scientific Videos based on Metadata Enrichment using Linked Open Data","date":"2018-06-19","arxiv_id":"1806.07309","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-adapted-beamforming-for-multi-channel","title":"Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition","date":"2018-06-19","arxiv_id":"1806.07407","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-tied-units-for-efficient-gating-in-lstm","title":"Semi-tied Units for Efficient Gating in LSTM and Highway Networks","date":"2018-06-18","arxiv_id":"1806.06513","repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-recurrent-neural-aligner-for","title":"Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin","date":"2018-06-17","arxiv_id":"1806.06342","repositories_listed":0,"syntology":null},{"url":null,"slug":"study-of-semi-supervised-approaches-to","title":"Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition","date":"2018-06-16","arxiv_id":"1806.06200","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-lip-reading-a-comparison-of-models-and","title":"Deep Lip Reading: a comparison of models and an online application","date":"2018-06-15","arxiv_id":"1806.06053","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapidnn-in-memory-deep-neural-network","title":"RAPIDNN: In-Memory Deep Neural Network Acceleration Framework","date":"2018-06-15","arxiv_id":"1806.05794","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearly-zero-shot-learning-for-semantic","title":"Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems","date":"2018-06-14","arxiv_id":"1806.05484","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-enhancement-augmentation-and","title":"A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition","date":"2018-06-13","arxiv_id":"1806.04841","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-adaptation-with-interpretable","title":"Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognition","date":"2018-06-13","arxiv_id":"1806.04872","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-end-to-end-speech-recognition","title":"Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages","date":"2018-06-12","arxiv_id":"1806.05059","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adversarial-training-for-accented","title":"Domain Adversarial Training for Accented Speech Recognition","date":"2018-06-07","arxiv_id":"1806.02786","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-augmentation-with-adversarial","title":"Training Augmentation with Adversarial Examples for Robust Speech Recognition","date":"2018-06-07","arxiv_id":"1806.02782","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-explainable-adversarial-robustness-metric","title":"An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks","date":"2018-06-05","arxiv_id":"1806.01477","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-automated-medical-scribe-for-documenting","title":"An automated medical scribe for documenting clinical encounters","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"binarized-lstm-language-model","title":"Binarized LSTM Language Model","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-sequence-learning-with-group","title":"Efficient Sequence Learning with Group Recurrent Networks","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-dictations-to-clinical-reports-using","title":"From dictations to clinical reports using machine translation","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-hidden-unit-contribution-for","title":"Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"making-convolutional-networks-recurrent-for","title":"Making Convolutional Networks Recurrent for Visual Sequence Learning","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-application-of-domain-dependent","title":"Practical Application of Domain Dependent Confidence Measurement for Spoken Language Understanding Systems","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"role-specific-language-models-for-processing","title":"Role-specific Language Models for Processing Recorded Neuropsychological Exams","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adagio-interactive-experimentation-with","title":"ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio","date":"2018-05-30","arxiv_id":"1805.11852","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-named-entity-extraction-from","title":"End-to-end named entity extraction from speech","date":"2018-05-30","arxiv_id":"1805.12045","repositories_listed":0,"syntology":null},{"url":null,"slug":"grow-and-prune-compact-fast-and-accurate","title":"Grow and Prune Compact, Fast, and Accurate LSTMs","date":"2018-05-30","arxiv_id":"1805.11797","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-lipreading-sentences-with-active","title":"Towards Lipreading Sentences with Active Appearance Models","date":"2018-05-29","arxiv_id":"1805.11688","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-speaker-segmentation-and","title":"Multimodal Speaker Segmentation and Diarization using Lexical and Acoustic Cues via Sequence to Sequence Neural Networks","date":"2018-05-28","arxiv_id":"1805.10731","repositories_listed":0,"syntology":null},{"url":null,"slug":"universality-of-deep-convolutional-neural","title":"Universality of Deep Convolutional Neural Networks","date":"2018-05-28","arxiv_id":"1805.10769","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-cnn-inference-on-fpgas-a-survey","title":"Accelerating CNN inference on FPGAs: A Survey","date":"2018-05-26","arxiv_id":"1806.01683","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-context-window-composition-for","title":"Automatic context window composition for distant speech recognition","date":"2018-05-26","arxiv_id":"1805.10498","repositories_listed":0,"syntology":null},{"url":null,"slug":"geometric-understanding-of-deep-learning","title":"Geometric Understanding of Deep Learning","date":"2018-05-26","arxiv_id":"1805.10451","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-dependent-modulation-of-the-visual","title":"Task-dependent modulation of the visual sensory thalamus assists visual-speech recognition","date":"2018-05-24","arxiv_id":"1805.05682","repositories_listed":0,"syntology":null},{"url":null,"slug":"asr-based-features-for-emotion-recognition-a","title":"ASR-based Features for Emotion Recognition: A Transfer Learning Approach","date":"2018-05-23","arxiv_id":"1805.09197","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-cross-modal-alignment-of-speech","title":"Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces","date":"2018-05-18","arxiv_id":"1805.07467","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-modeling-units-in-sequence-to","title":"A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese","date":"2018-05-16","arxiv_id":"1805.06239","repositories_listed":0,"syntology":null},{"url":null,"slug":"composing-finite-state-transducers-on-gpus","title":"Composing Finite State Transducers on GPUs","date":"2018-05-16","arxiv_id":"1805.06383","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-purely-end-to-end-system-for-multi-speaker","title":"A Purely End-to-end System for Multi-speaker Speech Recognition","date":"2018-05-15","arxiv_id":"1805.05826","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-asr-for-under-resourced-languages","title":"Improved ASR for Under-Resourced Languages Through Multi-Task Learning with Acoustic Landmarks","date":"2018-05-15","arxiv_id":"1805.05574","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparable-study-of-modeling-units-for-end","title":"A comparable study of modeling units for end-to-end Mandarin speech recognition","date":"2018-05-10","arxiv_id":"1805.03832","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-from-adult-to-children-for","title":"Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations","date":"2018-05-08","arxiv_id":"1805.03322","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-noise-robustness-of-acoustic-model","title":"Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training","date":"2018-05-02","arxiv_id":"1805.01357","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-pronunciation-modeling-of-swiss","title":"Data-Driven Pronunciation Modeling of Swiss German Dialectal Speech for Automatic Speech Recognition","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-corpora-in-mboshi-bantu-c25-congo","title":"Parallel Corpora in Mboshi (Bantu C25, Congo-Brazzaville)","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phonetically-balanced-code-mixed-speech","title":"Phonetically Balanced Code-Mixed Speech Corpus for Hindi-English Automatic Speech Recognition","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-documentation-of-icd-codes-with-far","title":"Automatic Documentation of ICD Codes with Far-Field Speech Recognition","date":"2018-04-30","arxiv_id":"1804.11046","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigations-on-end-to-end-audiovisual","title":"Investigations on End-to-End Audiovisual Fusion","date":"2018-04-30","arxiv_id":"1804.11127","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-persistent-rnns-squeezing-large","title":"Sparse Persistent RNNs: Squeezing Large Recurrent Networks On-Chip","date":"2018-04-26","arxiv_id":"1804.10223","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-multimodal-speech-recognition","title":"End-to-End Multimodal Speech Recognition","date":"2018-04-25","arxiv_id":"1804.09713","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-progresses-in-deep-learning-based","title":"Recent Progresses in Deep Learning based Acoustic Models (Updated)","date":"2018-04-25","arxiv_id":"1804.09298","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-information-theoretic-view-for-deep","title":"An Information-Theoretic View for Deep Learning","date":"2018-04-24","arxiv_id":"1804.09060","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-for-launch","title":"Automatic speech recognition for launch control center communication using recurrent neural networks with data augmentation and custom language model","date":"2018-04-24","arxiv_id":"1804.09552","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-head-decoder-for-end-to-end-speech","title":"Multi-Head Decoder for End-to-End Speech Recognition","date":"2018-04-22","arxiv_id":"1804.08050","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-compatibility-modeling-with-attentive","title":"Neural Compatibility Modeling with Attentive Knowledge Distillation","date":"2018-04-17","arxiv_id":"1805.00313","repositories_listed":0,"syntology":null},{"url":null,"slug":"precise-detection-of-speech-endpoints","title":"Precise Detection of Speech Endpoints Dynamically: A Wavelet Convolution based approach","date":"2018-04-17","arxiv_id":"1804.06159","repositories_listed":0,"syntology":null},{"url":"/paper/neural-network-language-modeling-with-letter","slug":"neural-network-language-modeling-with-letter","title":"Neural Network Language Modeling with Letter-based Features and Importance Sampling","date":"2018-04-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-recognition-using-time-delay-deep","title":"Language Recognition using Time Delay Deep Neural Network","date":"2018-04-13","arxiv_id":"1804.05000","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-snr-estimation-of-speech-signals-using","title":"Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks","date":"2018-04-12","arxiv_id":"1804.04353","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-as-an-interlingua-learning","title":"Vision as an Interlingua: Learning Multilingual Semantic Embeddings of Untranscribed Speech","date":"2018-04-09","arxiv_id":"1804.03052","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-learning-of-interactive-spoken-content","title":"Joint Learning of Interactive Spoken Content Retrieval and Trainable User Simulator","date":"2018-04-01","arxiv_id":"1804.00318","repositories_listed":0,"syntology":null},{"url":null,"slug":"espnet-end-to-end-speech-processing-toolkit","title":"ESPnet: End-to-End Speech Processing Toolkit","date":"2018-03-30","arxiv_id":"1804.00015","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unsupervised-automatic-speech","title":"Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only","date":"2018-03-29","arxiv_id":"1803.10952","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-speech-chain-with-one-shot-speaker","title":"Machine Speech Chain with One-shot Speaker Adaptation","date":"2018-03-28","arxiv_id":"1803.10525","repositories_listed":0,"syntology":null},{"url":"/paper/the-fifth-chime-speech-separation-and","slug":"the-fifth-chime-speech-separation-and","title":"The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines","date":"2018-03-28","arxiv_id":"1803.10609","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-discriminator-cyclegan-for","title":"A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation","date":"2018-03-27","arxiv_id":"1804.00522","repositories_listed":0,"syntology":null},{"url":"/paper/building-state-of-the-art-distant-speech","slug":"building-state-of-the-art-distant-speech","title":"Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline","date":"2018-03-27","arxiv_id":"1803.10109","repositories_listed":0,"syntology":null},{"url":null,"slug":"comprehending-real-numbers-development-of","title":"Comprehending Real Numbers: Development of Bengali Real Number Speech Corpus","date":"2018-03-27","arxiv_id":"1803.10136","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-data-augmentation-for-end-to-end","title":"Multi-Modal Data Augmentation for End-to-End ASR","date":"2018-03-27","arxiv_id":"1803.10299","repositories_listed":0,"syntology":null},{"url":null,"slug":"student-teacher-learning-for-blstm-mask-based","title":"Student-Teacher Learning for BLSTM Mask-based Speech Enhancement","date":"2018-03-27","arxiv_id":"1803.10013","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipping-free-attacks-against-artificial","title":"Clipping free attacks against artificial neural networks","date":"2018-03-26","arxiv_id":"1803.09468","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectral-feature-mapping-with-mimic-loss-for","title":"Spectral feature mapping with mimic loss for robust speech recognition","date":"2018-03-26","arxiv_id":"1803.09816","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-speech-to-text-translation","title":"Low-Resource Speech-to-Text Translation","date":"2018-03-24","arxiv_id":"1803.09164","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-robustness-of-features-and","title":"Exploring the robustness of features and enhancement on speech recognition systems in highly-reverberant real environments","date":"2018-03-23","arxiv_id":"1803.09013","repositories_listed":0,"syntology":null},{"url":null,"slug":"highly-reverberant-real-environment-database","title":"Highly-Reverberant Real Environment database: HRRE","date":"2018-03-23","arxiv_id":"1801.09651","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-feature-learning-using-cross-domain","title":"Acoustic feature learning using cross-domain articulatory measurements","date":"2018-03-19","arxiv_id":"1803.06805","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-to-text-and-text-to-speech-recognition","title":"Speech to text and text to speech recognition systems-Areview","date":"2018-03-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tbd-benchmarking-and-analyzing-deep-neural","title":"TBD: Benchmarking and Analyzing Deep Neural Network Training","date":"2018-03-16","arxiv_id":"1803.06905","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-connectionist-temporal","title":"Advancing Connectionist Temporal Classification With Attention Modeling","date":"2018-03-15","arxiv_id":"1803.05563","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-aware-design-of-a-deep-convolutional","title":"Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion","date":"2018-03-13","arxiv_id":"1803.04840","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-nodes-to-networks-evolving-recurrent","title":"From Nodes to Networks: Evolving Recurrent Neural Networks","date":"2018-03-12","arxiv_id":"1803.04439","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-keyword-spotting-through","title":"Speech Recognition: Keyword Spotting Through Image Recognition","date":"2018-03-10","arxiv_id":"1803.03759","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-domain-invariant-features-by","title":"Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition","date":"2018-03-07","arxiv_id":"1803.02551","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-modular-training-of-neural-acoustics-to","title":"On Modular Training of Neural Acoustics-to-Word Model for LVCSR","date":"2018-03-03","arxiv_id":"1803.01090","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-history-began-from-alexnet-a","title":"The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches","date":"2018-03-03","arxiv_id":"1803.01164","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-in-speech-recognition-and","title":"Challenges in Speech Recognition and Translation of High-Value Low-Density Polysynthetic Languages","date":"2018-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-automatic-speech-recognition-in","title":"Evaluating Automatic Speech Recognition in Translation","date":"2018-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-derivational-entropy-of-left-to-right","title":"On the Derivational Entropy of Left-to-Right Probabilistic Finite-State Automata and Hidden Markov Models","date":"2018-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-feed-forward-sequential-memory-networks","title":"Deep Feed-forward Sequential Memory Networks for Speech Synthesis","date":"2018-02-26","arxiv_id":"1802.09194","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-and-topic","title":"Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages","date":"2018-02-23","arxiv_id":"1802.08731","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-order-recurrent-neural-networks-for","title":"High Order Recurrent Neural Networks for Acoustic Modelling","date":"2018-02-22","arxiv_id":"1802.08314","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-predictive-coding-using-convolutional","title":"Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics","date":"2018-02-22","arxiv_id":"1802.07860","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-based-multi-lingual-low-resource","title":"Sequence-based Multi-lingual Low Resource Speech Recognition","date":"2018-02-21","arxiv_id":"1802.07420","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-knowledge-using-parallel-data-for","title":"Distilling Knowledge Using Parallel Data for Far-field Speech Recognition","date":"2018-02-20","arxiv_id":"1802.06941","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-tdnns-using-deep-kernels-and","title":"Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs","date":"2018-02-18","arxiv_id":"1802.06412","repositories_listed":0,"syntology":null},{"url":"/paper/visual-only-recognition-of-normal-whispered","slug":"visual-only-recognition-of-normal-whispered","title":"Visual-Only Recognition of Normal, Whispered and Silent Speech","date":"2018-02-18","arxiv_id":"1802.06399","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulatory-information-and-multiview","title":"Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition","date":"2018-02-16","arxiv_id":"1802.05853","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-dnn-output-layer-activations-a","title":"Interpreting DNN output layer activations: A strategy to cope with unseen data in speech recognition","date":"2018-02-16","arxiv_id":"1802.06861","repositories_listed":0,"syntology":null}],"record_sha256":"8b171b3488a3a5af8e32ebf45a2f4092d73541bad25c6712b6531716df9a21cb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}