{"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/53","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":53,"pages_in_order":58,"rows_per_page":100,"rows":[5201,5300],"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/52","next":"/task/speech-recognition-1/papers/54","papers":[{"url":null,"slug":"leveraging-deep-neural-network-activation","title":"Leveraging Deep Neural Network Activation Entropy to cope with Unseen Data in Speech Recognition","date":"2017-08-31","arxiv_id":"1708.09516","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-analysis-of-dnn-hmm","title":"Information Theoretic Analysis of DNN-HMM Acoustic Modeling","date":"2017-08-29","arxiv_id":"1709.01144","repositories_listed":0,"syntology":null},{"url":null,"slug":"mit-qcri-arabic-dialect-identification-system","title":"MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast Challenge","date":"2017-08-28","arxiv_id":"1709.00387","repositories_listed":0,"syntology":null},{"url":null,"slug":"cold-fusion-training-seq2seq-models-together","title":"Cold Fusion: Training Seq2Seq Models Together with Language Models","date":"2017-08-21","arxiv_id":"1708.06426","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-microsoft-2017-conversational-speech","title":"The Microsoft 2017 Conversational Speech Recognition System","date":"2017-08-21","arxiv_id":"1708.06073","repositories_listed":0,"syntology":null},{"url":null,"slug":"future-word-contexts-in-neural-network","title":"Future Word Contexts in Neural Network Language Models","date":"2017-08-18","arxiv_id":"1708.05592","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-residual-lstm-architecture-for","title":"An Improved Residual LSTM Architecture for Acoustic Modeling","date":"2017-08-17","arxiv_id":"1708.05682","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-domain-adaptation-via-teacher","title":"Large-Scale Domain Adaptation via Teacher-Student Learning","date":"2017-08-17","arxiv_id":"1708.05466","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogue-act-segmentation-for-vietnamese","title":"Dialogue Act Segmentation for Vietnamese Human-Human Conversational Texts","date":"2017-08-16","arxiv_id":"1708.04765","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-decoding-strategies-for-ctc","title":"Comparison of Decoding Strategies for CTC Acoustic Models","date":"2017-08-15","arxiv_id":"1708.04469","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-speaker-independent-lipreading-with","title":"Improving Speaker-Independent Lipreading with Domain-Adversarial Training","date":"2017-08-04","arxiv_id":"1708.01565","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-neural-segmental-models-for-speech","title":"End-to-End Neural Segmental Models for Speech Recognition","date":"2017-08-01","arxiv_id":"1708.00531","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-neural-transducers-for-end-to-end","title":"Exploring Neural Transducers for End-to-End Speech Recognition","date":"2017-07-24","arxiv_id":"1707.07413","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-with-neural-trans","title":"Language modeling with Neural trans-dimensional random fields","date":"2017-07-23","arxiv_id":"1707.07240","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-end-to-end-speech-recognition","title":"Attention-Based End-to-End Speech Recognition on Voice Search","date":"2017-07-22","arxiv_id":"1707.07167","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-joint-modeling-in-unsupervised","title":"Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition","date":"2017-07-21","arxiv_id":"1707.07048","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-layer-normalization-for-adaptive","title":"Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition","date":"2017-07-19","arxiv_id":"1707.06065","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-accurate-oov-decoder-on-high-level","title":"Fast and Accurate OOV Decoder on High-Level Features","date":"2017-07-19","arxiv_id":"1707.06195","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-channel-multi-talker-speech","title":"Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training","date":"2017-07-19","arxiv_id":"1707.06527","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-for-robust","title":"Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation","date":"2017-07-19","arxiv_id":"1707.06265","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoding-word-confusion-networks-with","title":"Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking","date":"2017-07-18","arxiv_id":"1707.05853","repositories_listed":0,"syntology":null},{"url":null,"slug":"houdini-fooling-deep-structured-prediction","title":"Houdini: Fooling Deep Structured Prediction Models","date":"2017-07-17","arxiv_id":"1707.05373","repositories_listed":0,"syntology":null},{"url":null,"slug":"listening-while-speaking-speech-chain-by-deep","title":"Listening while Speaking: Speech Chain by Deep Learning","date":"2017-07-16","arxiv_id":"1707.04879","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-with-very-large","title":"Automatic Speech Recognition with Very Large Conversational Finnish and Estonian Vocabularies","date":"2017-07-13","arxiv_id":"1707.04227","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-causes-of-reformulation-in","title":"Predicting Causes of Reformulation in Intelligent Assistants","date":"2017-07-13","arxiv_id":"1707.03968","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-machine-learning-integrating","title":"Multimodal Machine Learning: Integrating Language, Vision and Speech","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"safetynets-verifiable-execution-of-deep","title":"SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud","date":"2017-06-30","arxiv_id":"1706.10268","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-computation-and-memory-efficient","title":"Toward Computation and Memory Efficient Neural Network Acoustic Models with Binary Weights and Activations","date":"2017-06-28","arxiv_id":"1706.09453","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-modeling-using-a-shallow-cnn-htsvm","title":"Acoustic Modeling Using a Shallow CNN-HTSVM Architecture","date":"2017-06-27","arxiv_id":"1706.09055","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-variational-em-method-for-pole-zero","title":"A Variational EM Method for Pole-Zero Modeling of Speech with Mixed Block Sparse and Gaussian Excitation","date":"2017-06-24","arxiv_id":"1706.07927","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-quality-estimation-for-asr-system","title":"Automatic Quality Estimation for ASR System Combination","date":"2017-06-22","arxiv_id":"1706.07238","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-time-frequency-representations","title":"Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks","date":"2017-06-22","arxiv_id":"1706.07156","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-dropout-learning-regarded-as","title":"Analysis of dropout learning regarded as ensemble learning","date":"2017-06-20","arxiv_id":"1706.06859","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-online-sequence-to-sequence-model-for","title":"An online sequence-to-sequence model for noisy speech recognition","date":"2017-06-16","arxiv_id":"1706.06428","repositories_listed":0,"syntology":null},{"url":null,"slug":"modelling-prosodic-structure-using-artificial","title":"Modelling prosodic structure using Artificial Neural Networks","date":"2017-06-13","arxiv_id":"1706.03952","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-data-driven-lexicon-learning-based","title":"Acoustic data-driven lexicon learning based on a greedy pronunciation selection framework","date":"2017-06-12","arxiv_id":"1706.03747","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-neural-networks-for-subvocal","title":"End-to-end neural networks for subvocal speech recognition","date":"2017-06-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-expected-word-error-rate-via","title":"Optimizing expected word error rate via sampling for speech recognition","date":"2017-06-08","arxiv_id":"1706.02776","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-types-of-convolution-in-deep","title":"Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition","date":"2017-06-07","arxiv_id":"1706.02901","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-of-heterogeneous-corpora-for-training","title":"Using of heterogeneous corpora for training of an ASR system","date":"2017-06-01","arxiv_id":"1706.00321","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-environmentally-robust","title":"Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments","date":"2017-05-30","arxiv_id":"1705.10874","repositories_listed":0,"syntology":null},{"url":null,"slug":"dnn-based-uncertainty-estimation-for-weighted","title":"DNN-based uncertainty estimation for weighted DNN-HMM ASR","date":"2017-05-29","arxiv_id":"1705.10368","repositories_listed":0,"syntology":null},{"url":null,"slug":"asr-error-management-for-improving-spoken","title":"ASR error management for improving spoken language understanding","date":"2017-05-26","arxiv_id":"1705.09515","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-model-training-for-unbounded","title":"Semi-Supervised Model Training for Unbounded Conversational Speech Recognition","date":"2017-05-26","arxiv_id":"1705.09724","repositories_listed":0,"syntology":null},{"url":null,"slug":"anti-spoofing-methods-for-automatic","title":"Anti-spoofing Methods for Automatic SpeakerVerification System","date":"2017-05-24","arxiv_id":"1705.08865","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-monotonic-attention-mechanism-for-end","title":"Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing","date":"2017-05-23","arxiv_id":"1705.08091","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-knowledge-graph-based-speech","title":"Towards a Knowledge Graph based Speech Interface","date":"2017-05-23","arxiv_id":"1705.09222","repositories_listed":0,"syntology":null},{"url":null,"slug":"use-of-knowledge-graph-in-rescoring-the-n","title":"Use of Knowledge Graph in Rescoring the N-Best List in Automatic Speech Recognition","date":"2017-05-22","arxiv_id":"1705.08018","repositories_listed":0,"syntology":null},{"url":null,"slug":"voltage-driven-domain-wall-motion-based-neuro","title":"Voltage-Driven Domain-Wall Motion based Neuro-Synaptic Devices for Dynamic On-line Learning","date":"2017-05-19","arxiv_id":"1705.06942","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-hard-alignments-with-variational","title":"Learning Hard Alignments with Variational Inference","date":"2017-05-16","arxiv_id":"1705.05524","repositories_listed":0,"syntology":null},{"url":null,"slug":"talking-to-your-tv-context-aware-voice-search","title":"Talking to Your TV: Context-Aware Voice Search with Hierarchical Recurrent Neural Networks","date":"2017-05-13","arxiv_id":"1705.04892","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-model-of-a-pronunciation-lexicon","title":"A Generative Model of a Pronunciation Lexicon for Hindi","date":"2017-05-06","arxiv_id":"1705.02452","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-batch-construction","title":"A comprehensive study of batch construction strategies for recurrent neural networks in MXNet","date":"2017-05-05","arxiv_id":"1705.02414","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-in-the-automotive-industry","title":"Deep Learning in the Automotive Industry: Applications and Tools","date":"2017-04-30","arxiv_id":"1705.00346","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-personal-assistant-with-knowledge","title":"Intelligent Personal Assistant with Knowledge Navigation","date":"2017-04-28","arxiv_id":"1704.08950","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-viseme-vocabulary-construction-to","title":"Automatic Viseme Vocabulary Construction to Enhance Continuous Lip-reading","date":"2017-04-26","arxiv_id":"1704.08035","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-estimating-the-upper-bound-of-visual","title":"Towards Estimating the Upper Bound of Visual-Speech Recognition: The Visual Lip-Reading Feasibility Database","date":"2017-04-26","arxiv_id":"1704.08028","repositories_listed":0,"syntology":null},{"url":null,"slug":"approxdbn-approximate-computing-for","title":"ApproxDBN: Approximate Computing for Discriminative Deep Belief Networks","date":"2017-04-13","arxiv_id":"1704.03993","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobile-keyboard-input-decoding-with-finite","title":"Mobile Keyboard Input Decoding with Finite-State Transducers","date":"2017-04-13","arxiv_id":"1704.03987","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-multimodal-representation-learning-from","title":"Deep Multimodal Representation Learning from Temporal Data","date":"2017-04-11","arxiv_id":"1704.03152","repositories_listed":0,"syntology":null},{"url":null,"slug":"voice-conversion-using-sequence-to-sequence","title":"Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior Probabilities","date":"2017-04-10","arxiv_id":"1704.02360","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-outlyingness-matrix-for-multivariate","title":"An Outlyingness Matrix for Multivariate Functional Data Classification","date":"2017-04-09","arxiv_id":"1704.02568","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitask-learning-with-low-level-auxiliary","title":"Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition","date":"2017-04-05","arxiv_id":"1704.01631","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-generalization-and-regularization-in-deep","title":"On Generalization and Regularization in Deep Learning","date":"2017-04-05","arxiv_id":"1704.01312","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-automatic-speech-recognition","title":"An enhanced automatic speech recognition system for Arabic","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-unsupervised-speaker-clustering-technique","title":"An Unsupervised Speaker Clustering Technique based on SOM and I-vectors for Speech Recognition Systems","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aoh-ive-heard-that-before-modelling-own","title":"``Oh, I've Heard That Before'': Modelling Own-Dialect Bias After Perceptual Learning by Weighting Training Data","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cassandra-a-multipurpose-configurable-voice","title":"CASSANDRA: A multipurpose configurable voice-enabled human-computer-interface","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-word-embeddings-for-low","title":"Cross-Lingual Word Embeddings for Low-Resource Language Modeling","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-and-dialect-bias-in-youtubes-automatic","title":"Gender and Dialect Bias in YouTube's Automatic Captions","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-summa-platform-prototype","title":"The SUMMA Platform Prototype","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topologynet-topology-based-deep-convolutional","title":"TopologyNet: Topology based deep convolutional neural networks for biomolecular property predictions","date":"2017-03-31","arxiv_id":"1704.00063","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplified-end-to-end-mmi-training-and-voting","title":"Simplified End-to-End MMI Training and Voting for ASR","date":"2017-03-30","arxiv_id":"1703.10356","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-similarity-functions-for","title":"Learning Similarity Functions for Pronunciation Variations","date":"2017-03-28","arxiv_id":"1703.09817","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-processing-of-deep-neural-networks","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","date":"2017-03-27","arxiv_id":"1703.09039","repositories_listed":0,"syntology":null},{"url":null,"slug":"batch-normalized-joint-training-for-dnn-based","title":"Batch-normalized joint training for DNN-based distant speech recognition","date":"2017-03-24","arxiv_id":"1703.08471","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-network-of-deep-neural-networks-for-distant","title":"A network of deep neural networks for distant speech recognition","date":"2017-03-23","arxiv_id":"1703.08002","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-acoustics-to-word-models-for-english","title":"Direct Acoustics-to-Word Models for English Conversational Speech Recognition","date":"2017-03-22","arxiv_id":"1703.07754","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-multi-talker-speech-with","title":"Recognizing Multi-talker Speech with Permutation Invariant Training","date":"2017-03-22","arxiv_id":"1704.01985","repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-identification-for-speech-without-asr","title":"Topic Identification for Speech without ASR","date":"2017-03-22","arxiv_id":"1703.07476","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-digital-neuromorphic-architecture","title":"A Digital Neuromorphic Architecture Efficiently Facilitating Complex Synaptic Response Functions Applied to Liquid State Machines","date":"2017-03-21","arxiv_id":"1704.08306","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-lstm-for-large-vocabulary-continuous","title":"Deep LSTM for Large Vocabulary Continuous Speech Recognition","date":"2017-03-21","arxiv_id":"1703.07090","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-evaluation-of-parallel-training","title":"Empirical Evaluation of Parallel Training Algorithms on Acoustic Modeling","date":"2017-03-17","arxiv_id":"1703.05880","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-recurrent-neural-networks-for-2","title":"Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting","date":"2017-03-15","arxiv_id":"1703.05390","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-learning-of-correlated-sequence","title":"Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks","date":"2017-03-14","arxiv_id":"1703.04650","repositories_listed":0,"syntology":null},{"url":null,"slug":"multichannel-end-to-end-speech-recognition","title":"Multichannel End-to-end Speech Recognition","date":"2017-03-14","arxiv_id":"1703.04783","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-echo-state-network-output-layer","title":"Comparison of echo state network output layer classification methods on noisy data","date":"2017-03-13","arxiv_id":"1703.04496","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reservoir-computing-using-cellular","title":"Deep Reservoir Computing Using Cellular Automata","date":"2017-03-08","arxiv_id":"1703.02806","repositories_listed":0,"syntology":null},{"url":"/paper/english-conversational-telephone-speech","slug":"english-conversational-telephone-speech","title":"English Conversational Telephone Speech Recognition by Humans and Machines","date":"2017-03-06","arxiv_id":"1703.02136","repositories_listed":0,"syntology":null},{"url":null,"slug":"exponential-moving-average-model-in-parallel","title":"Exponential Moving Average Model in Parallel Speech Recognition Training","date":"2017-03-03","arxiv_id":"1703.01024","repositories_listed":0,"syntology":null},{"url":null,"slug":"gram-ctc-automatic-unit-selection-and-target","title":"Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling","date":"2017-03-01","arxiv_id":"1703.00096","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-representation-of-layered-neural","title":"Modular Representation of Layered Neural Networks","date":"2017-03-01","arxiv_id":"1703.00168","repositories_listed":0,"syntology":null},{"url":null,"slug":"chaos-a-parallelization-scheme-for-training","title":"CHAOS: A Parallelization Scheme for Training Convolutional Neural Networks on Intel Xeon Phi","date":"2017-02-25","arxiv_id":"1702.07908","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-convolutional-ctc-networks-for","title":"Residual Convolutional CTC Networks for Automatic Speech Recognition","date":"2017-02-24","arxiv_id":"1702.07793","repositories_listed":0,"syntology":null},{"url":null,"slug":"pronunciation-recognition-of-english-phonemes","title":"Pronunciation recognition of English phonemes /\\textipa{@}/, /æ/, /\\textipa{A}:/ and /\\textipa{2}/ using Formants and Mel Frequency Cepstral Coefficients","date":"2017-02-23","arxiv_id":"1702.07071","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitask-learning-with-ctc-and-segmental-crf","title":"Multitask Learning with CTC and Segmental CRF for Speech Recognition","date":"2017-02-21","arxiv_id":"1702.06378","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-case-study-on-using-speech-to-translation","title":"A case study on using speech-to-translation alignments for language documentation","date":"2017-02-14","arxiv_id":"1702.04372","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-relevance-of-auditory-based-gabor","title":"On the Relevance of Auditory-Based Gabor Features for Deep Learning in Automatic Speech Recognition","date":"2017-02-14","arxiv_id":"1702.04333","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-speech-to-text-translation-without","title":"Towards speech-to-text translation without speech recognition","date":"2017-02-13","arxiv_id":"1702.03856","repositories_listed":0,"syntology":null},{"url":null,"slug":"search-intelligence-deep-learning-for","title":"Search Intelligence: Deep Learning For Dominant Category Prediction","date":"2017-02-06","arxiv_id":"1702.01717","repositories_listed":0,"syntology":null}],"record_sha256":"e8c943ad6bc0a3ffe42f3c7bdf854683bdfd21a295a36b4f9248c1251cedba3c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}