{"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/54","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":54,"pages_in_order":58,"rows_per_page":100,"rows":[5301,5400],"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/53","next":"/task/speech-recognition-1/papers/55","papers":[{"url":null,"slug":"structural-analysis-of-hindi-phonetics-and-a","title":"Structural Analysis of Hindi Phonetics and A Method for Extraction of Phonetically Rich Sentences from a Very Large Hindi Text Corpus","date":"2017-01-30","arxiv_id":"1701.08655","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-bengali-phoneme","title":"A Comprehensive Survey on Bengali Phoneme Recognition","date":"2017-01-27","arxiv_id":"1701.08156","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-word-like-units-from-joint-audio","title":"Learning Word-Like Units from Joint Audio-Visual Analysis","date":"2017-01-25","arxiv_id":"1701.07481","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-network-guided-proof-search","title":"Deep Network Guided Proof Search","date":"2017-01-24","arxiv_id":"1701.06972","repositories_listed":0,"syntology":null},{"url":null,"slug":"lyrics-to-audio-alignment-by-unsupervised","title":"Lyrics-to-Audio Alignment by Unsupervised Discovery of Repetitive Patterns in Vowel Acoustics","date":"2017-01-21","arxiv_id":"1701.06078","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-visual-speech-recognition-with","title":"End-To-End Visual Speech Recognition With LSTMs","date":"2017-01-20","arxiv_id":"1701.05847","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-computational-chemistry","title":"Deep Learning for Computational Chemistry","date":"2017-01-17","arxiv_id":"1701.04503","repositories_listed":0,"syntology":null},{"url":null,"slug":"auxiliary-multimodal-lstm-for-audio-visual","title":"Auxiliary Multimodal LSTM for Audio-visual Speech Recognition and Lipreading","date":"2017-01-16","arxiv_id":"1701.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-asr-free-keyword-search-from","title":"End-to-End ASR-free Keyword Search from Speech","date":"2017-01-13","arxiv_id":"1701.04313","repositories_listed":0,"syntology":null},{"url":null,"slug":"kernel-approximation-methods-for-speech","title":"Kernel Approximation Methods for Speech Recognition","date":"2017-01-13","arxiv_id":"1701.03577","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-non-homogeneous-markov-models-via","title":"Bayesian Non-Homogeneous Markov Models via Polya-Gamma Data Augmentation with Applications to Rainfall Modeling","date":"2017-01-11","arxiv_id":"1701.02856","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoding-with-finite-state-transducers-on","title":"Decoding with Finite-State Transducers on GPUs","date":"2017-01-11","arxiv_id":"1701.03038","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-of-deep-neural-networks","title":"Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition","date":"2017-01-10","arxiv_id":"1701.02477","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-time-series-analysis","title":"Deep Learning for Time-Series Analysis","date":"2017-01-07","arxiv_id":"1701.01887","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-affective-computational-model-for-machine","title":"An affective computational model for machine consciousness","date":"2017-01-02","arxiv_id":"1701.00349","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-databases-for-designing-high","title":"Graph Databases for Designing High-Performance Speech Recognition Grammars","date":"2017-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"delta-networks-for-optimized-recurrent","title":"Delta Networks for Optimized Recurrent Network Computation","date":"2016-12-16","arxiv_id":"1612.05571","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-language-level-information-into","title":"Incorporating Language Level Information into Acoustic Models","date":"2016-12-14","arxiv_id":"1612.04744","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-deep-stacking-networks-for-speech","title":"Recurrent Deep Stacking Networks for Speech Recognition","date":"2016-12-14","arxiv_id":"1612.04675","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-automatic-speech-recognition","title":"Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures","date":"2016-12-13","arxiv_id":"1612.03990","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-for-speech-recognition-the","title":"Active Learning for Speech Recognition: the Power of Gradients","date":"2016-12-10","arxiv_id":"1612.03226","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-decoding-and-language-model","title":"Towards better decoding and language model integration in sequence to sequence models","date":"2016-12-08","arxiv_id":"1612.02695","repositories_listed":0,"syntology":null},{"url":"/paper/a-non-expert-kaldi-recipe-for-vietnamese","slug":"a-non-expert-kaldi-recipe-for-vietnamese","title":"A non-expert Kaldi recipe for Vietnamese Speech Recognition System","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a12c-aa-a-c314a14aeae3e34-e-the-use-of","title":"使用字典學習法於強健性語音辨識 (The Use of Dictionary Learning Approach for Robustness Speech Recognition) [In Chinese]","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-and-effective-online-sentence","title":"An Efficient and Effective Online Sentence Segmenter for Simultaneous Interpretation","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-of-bppts-indonesian-language","title":"An Overview of BPPT's Indonesian Language Resources","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-language-weka-based-dialect-classifier","title":"Arabic Language WEKA-Based Dialect Classifier for Arabic Automatic Speech Recognition Transcripts","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-speech-unit-delimitation-in-spoken","title":"Automated speech-unit delimitation in spoken learner English","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-errors-as-a","title":"Automatic Speech Recognition Errors as a Predictor of L2 Listening Difficulties","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-grapheme-to-phoneme-conversion","title":"Comparison of Grapheme-to-Phoneme Conversion Methods on a Myanmar Pronunciation Dictionary","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eaaaaa-ceccc2e-e2a-ae-c-14eeae3e34-ea1c-c","title":"融合多任務學習類神經網路聲學模型訓練於會議語音辨識之研究 (Leveraging Multi-Task Learning with Neural Network Based Acoustic Modeling for Improved Meeting Speech Recognition) [In Chinese]","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ese-efficient-speech-recognition-engine-with","title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA","date":"2016-12-01","arxiv_id":"1612.00694","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightly-supervised-quality-estimation","title":"Lightly Supervised Quality Estimation","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"microsoft-speech-language-translation-mslt","title":"Microsoft Speech Language Translation (MSLT) Corpus: The IWSLT 2016 release for English, French and German","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"racai-entry-for-the-iwslt-2016-shared-task","title":"RACAI Entry for the IWSLT 2016 Shared Task","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ioit-english-asr-system-for-iwslt-2016","title":"The IOIT English ASR system for IWSLT 2016","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-iwslt-2016-evaluation-campaign","title":"The IWSLT 2016 Evaluation Campaign","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-rwth-aachen-lvcsr-system-for-iwslt-2016","title":"The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-improving-low-resource-speech","title":"Towards Improving Low-Resource Speech Recognition Using Articulatory and Language Features","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-text-to-speech-alignment","title":"Weakly-supervised text-to-speech alignment confidence measure","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zara-a-virtual-interactive-dialogue-system","title":"Zara: A Virtual Interactive Dialogue System Incorporating Emotion, Sentiment and Personality Recognition","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-prediction-on-sequences-with-time","title":"Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition","date":"2016-11-28","arxiv_id":"1611.09288","repositories_listed":0,"syntology":null},{"url":null,"slug":"invariant-representations-for-noisy-speech","title":"Invariant Representations for Noisy Speech Recognition","date":"2016-11-27","arxiv_id":"1612.01928","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-on-data-representation-learning","title":"An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning","date":"2016-11-25","arxiv_id":"1611.08331","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-the-predictions-of-complex-ml","title":"Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation","date":"2016-11-24","arxiv_id":"1611.08191","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-recurrent-convolutional-neural-network","title":"Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition","date":"2016-11-22","arxiv_id":"1611.07174","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-distill-the-essence-vector","title":"Learning to Distill: The Essence Vector Modeling Framework","date":"2016-11-22","arxiv_id":"1611.07206","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-end-to-end-deep-audiovisual-speech","title":"Robust end-to-end deep audiovisual speech recognition","date":"2016-11-21","arxiv_id":"1611.06986","repositories_listed":0,"syntology":null},{"url":null,"slug":"compacting-neural-network-classifiers-via","title":"Compacting Neural Network Classifiers via Dropout Training","date":"2016-11-18","arxiv_id":"1611.06148","repositories_listed":0,"syntology":null},{"url":null,"slug":"increasing-the-interpretability-of-recurrent-1","title":"Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models","date":"2016-11-18","arxiv_id":"1611.05934","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-information-retrieval-a-literature","title":"Neural Information Retrieval: A Literature Review","date":"2016-11-18","arxiv_id":"1611.06792","repositories_listed":0,"syntology":null},{"url":"/paper/lip-reading-sentences-in-the-wild","slug":"lip-reading-sentences-in-the-wild","title":"Lip Reading Sentences in the Wild","date":"2016-11-16","arxiv_id":"1611.05358","repositories_listed":0,"syntology":null},{"url":null,"slug":"tricks-from-deep-learning","title":"Tricks from Deep Learning","date":"2016-11-10","arxiv_id":"1611.03777","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-speech-recognition-using-deep","title":"Audio Visual Speech Recognition using Deep Recurrent Neural Networks","date":"2016-11-09","arxiv_id":"1611.02879","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-recognition-of-child-speech-for","title":"Automatic recognition of child speech for robotic applications in noisy environments","date":"2016-11-08","arxiv_id":"1611.02695","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-acoustic-word-embeddings","title":"Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches","date":"2016-11-08","arxiv_id":"1611.02550","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-networks-designing-neural-networks","title":"Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimization","date":"2016-11-07","arxiv_id":"1611.02120","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-transition-based-dependency-parsing-and","title":"Joint Transition-based Dependency Parsing and Disfluency Detection for Automatic Speech Recognition Texts","date":"2016-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-speech-recognizer-acoustic-to-word","title":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","date":"2016-10-31","arxiv_id":"1610.09975","repositories_listed":0,"syntology":null},{"url":null,"slug":"still-not-there-comparing-traditional","title":"Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks","date":"2016-10-25","arxiv_id":"1610.07796","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-training-approaches-for","title":"End-to-End Training Approaches for Discriminative Segmental Models","date":"2016-10-21","arxiv_id":"1610.06700","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodiment-of-learning-in-electro-optical","title":"Embodiment of Learning in Electro-Optical Signal Processors","date":"2016-10-20","arxiv_id":"1610.06269","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-training-of-an-opto-electronic","title":"Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation","date":"2016-10-20","arxiv_id":"1610.06268","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bayesian-approach-to-estimation-of-speaker","title":"A Bayesian Approach to Estimation of Speaker Normalization Parameters","date":"2016-10-19","arxiv_id":"1610.05948","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-and-sparse-soft-targets-to-learn","title":"Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models","date":"2016-10-18","arxiv_id":"1610.05688","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-footprint-highway-deep-neural-networks","title":"Small-footprint Highway Deep Neural Networks for Speech Recognition","date":"2016-10-18","arxiv_id":"1610.05812","repositories_listed":0,"syntology":null},{"url":"/paper/achieving-human-parity-in-conversational","slug":"achieving-human-parity-in-conversational","title":"Achieving Human Parity in Conversational Speech Recognition","date":"2016-10-17","arxiv_id":"1610.05256","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-attention-based-distant-speech","title":"End-to-end attention-based distant speech recognition with Highway LSTM","date":"2016-10-17","arxiv_id":"1610.05361","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-sentence-and-context","title":"Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding","date":"2016-10-13","arxiv_id":"1610.04120","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-short-term-memory-based-convolutional","title":"Long Short-Term Memory based Convolutional Recurrent Neural Networks for Large Vocabulary Speech Recognition","date":"2016-10-11","arxiv_id":"1610.03165","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-instance-learning-convolutional","title":"Multiple Instance Learning Convolutional Neural Networks for Object Recognition","date":"2016-10-11","arxiv_id":"1610.03155","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-sequence-decompositions","title":"Latent Sequence Decompositions","date":"2016-10-10","arxiv_id":"1610.03035","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semantic-analyzer-for-the-comprehension-of","title":"A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech","date":"2016-10-08","arxiv_id":"1610.02493","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-of-computational-processing-of","title":"Challenges of Computational Processing of Code-Switching","date":"2016-10-07","arxiv_id":"1610.02213","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-non-invertible-data-transformations-to","title":"Using Non-invertible Data Transformations to Build Adversarial-Robust Neural Networks","date":"2016-10-06","arxiv_id":"1610.01934","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversary-resistant-deep-neural-networks-with","title":"Adversary Resistant Deep Neural Networks with an Application to Malware Detection","date":"2016-10-05","arxiv_id":"1610.01239","repositories_listed":0,"syntology":null},{"url":null,"slug":"monaural-multi-talker-speech-recognition","title":"Monaural Multi-Talker Speech Recognition using Factorial Speech Processing Models","date":"2016-10-05","arxiv_id":"1610.01367","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-learning-with-sparse","title":"Semi-supervised Learning with Sparse Autoencoders in Phone Classification","date":"2016-10-03","arxiv_id":"1610.00520","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-tour-of-tensorflow","title":"A Tour of TensorFlow","date":"2016-10-01","arxiv_id":"1610.01178","repositories_listed":0,"syntology":null},{"url":null,"slug":"a12c-aa-a-c314a14aeae3e34-ethe-use-of","title":"使用字典學習法於強健性語音辨識(The Use of Dictionary Learning Approach for Robustness Speech Recognition) [In Chinese]","date":"2016-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eaaaaa-ceccc2e-e2a-ae-c-14eeae3e34-ea1c","title":"融合多任務學習類神經網路聲學模型訓練於會議語音辨識之研究(Leveraging Multi-task Learning with Neural Network Based Acoustic Modeling for Improved Meeting Speech Recognition) [In Chinese]","date":"2016-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fpga-based-low-power-speech-recognition-with","title":"FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks","date":"2016-09-30","arxiv_id":"1610.00552","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-visualization-for-gated-recurrent","title":"Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition","date":"2016-09-28","arxiv_id":"1609.08789","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-recurrent-model-for-true","title":"Multi-task Recurrent Model for True Multilingual Speech Recognition","date":"2016-09-27","arxiv_id":"1609.08337","repositories_listed":0,"syntology":null},{"url":null,"slug":"oc16-ce80-a-chinese-english-mixlingual","title":"OC16-CE80: A Chinese-English Mixlingual Database and A Speech Recognition Baseline","date":"2016-09-27","arxiv_id":"1609.08412","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimally-supervised-written-to-spoken-text","title":"Minimally Supervised Written-to-Spoken Text Normalization","date":"2016-09-21","arxiv_id":"1609.06649","repositories_listed":0,"syntology":null},{"url":null,"slug":"advances-in-all-neural-speech-recognition","title":"Advances in All-Neural Speech Recognition","date":"2016-09-19","arxiv_id":"1609.05935","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-spoken-content-retrieval-by-deep","title":"Interactive Spoken Content Retrieval by Deep Reinforcement Learning","date":"2016-09-16","arxiv_id":"1609.05234","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adaptive-psychoacoustic-model-for","title":"An Adaptive Psychoacoustic Model for Automatic Speech Recognition","date":"2016-09-14","arxiv_id":"1609.04417","repositories_listed":0,"syntology":null},{"url":null,"slug":"character-level-language-modeling-with","title":"Character-Level Language Modeling with Hierarchical Recurrent Neural Networks","date":"2016-09-13","arxiv_id":"1609.03777","repositories_listed":0,"syntology":null},{"url":"/paper/the-microsoft-2016-conversational-speech","slug":"the-microsoft-2016-conversational-speech","title":"The Microsoft 2016 Conversational Speech Recognition System","date":"2016-09-12","arxiv_id":"1609.03528","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-three-dimensional-approach-to-visual-speech","title":"A three-dimensional approach to Visual Speech Recognition using Discrete Cosine Transforms","date":"2016-09-07","arxiv_id":"1609.01932","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-teacher-questions-using-automatic","title":"Identifying Teacher Questions Using Automatic Speech Recognition in Classrooms","date":"2016-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-augmented-maximum-likelihood-for","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","date":"2016-09-01","arxiv_id":"1609.00150","repositories_listed":0,"syntology":null},{"url":null,"slug":"temperature-based-deep-boltzmann-machines","title":"Temperature-Based Deep Boltzmann Machines","date":"2016-08-27","arxiv_id":"1608.07719","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-of-jointly-trained-deep-neural","title":"Ensemble of Jointly Trained Deep Neural Network-Based Acoustic Models for Reverberant Speech Recognition","date":"2016-08-17","arxiv_id":"1608.04983","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoder-decoder-with-focus-mechanism-for","title":"Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding","date":"2016-08-06","arxiv_id":"1608.02097","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-online-alignments-with-continuous","title":"Learning Online Alignments with Continuous Rewards Policy Gradient","date":"2016-08-03","arxiv_id":"1608.01281","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-segmental-cascades-for-speech","title":"Efficient Segmental Cascades for Speech Recognition","date":"2016-08-02","arxiv_id":"1608.00929","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-small-footprint","title":"Knowledge Distillation for Small-footprint Highway Networks","date":"2016-08-02","arxiv_id":"1608.00892","repositories_listed":0,"syntology":null}],"record_sha256":"2c9be5823cd949a2e1548a371d5bc0a4ee8fd5b460f67d234f51e9767d2ee902","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}