{"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/49","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":49,"pages_in_order":58,"rows_per_page":100,"rows":[4801,4900],"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/48","next":"/task/speech-recognition-1/papers/50","papers":[{"url":null,"slug":"progressive-label-distillation-learning-input","title":"Progressive Label Distillation: Learning Input-Efficient Deep Neural Networks","date":"2019-01-26","arxiv_id":"1901.09135","repositories_listed":0,"syntology":null},{"url":null,"slug":"weighted-sampling-audio-adversarial-example","title":"Weighted-Sampling Audio Adversarial Example Attack","date":"2019-01-26","arxiv_id":"1901.10300","repositories_listed":0,"syntology":null},{"url":null,"slug":"overfitting-mechanism-and-avoidance-in-deep","title":"Overfitting Mechanism and Avoidance in Deep Neural Networks","date":"2019-01-19","arxiv_id":"1901.06566","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-performance-using-approximate","title":"Predicting Performance using Approximate State Space Model for Liquid State Machines","date":"2019-01-18","arxiv_id":"1901.06240","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-the-recent-architectures-of-deep","title":"A Survey of the Recent Architectures of Deep Convolutional Neural Networks","date":"2019-01-17","arxiv_id":"1901.06032","repositories_listed":0,"syntology":null},{"url":null,"slug":"phoneme-based-persian-speech-recognition","title":"Phoneme-Based Persian Speech Recognition","date":"2019-01-15","arxiv_id":"1901.04699","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-noise-robustness-of-automatic","title":"Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning","date":"2019-01-05","arxiv_id":"1901.02348","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-adaptation-for-end-to-end-ctc-models","title":"Speaker Adaptation for End-to-End CTC Models","date":"2019-01-04","arxiv_id":"1901.01239","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-speech-enhancement-for-reverberated-and","title":"Deep Speech Enhancement for Reverberated and Noisy Signals using Wide Residual Networks","date":"2019-01-03","arxiv_id":"1901.00660","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-learning-approach-for-similar","title":"A Deep Learning Approach for Similar Languages, Varieties and Dialects","date":"2019-01-02","arxiv_id":"1901.00297","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-interpretability-of-deep-neural","title":"Improving the Interpretability of Deep Neural Networks with Knowledge Distillation","date":"2018-12-28","arxiv_id":"1812.10924","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-the-state-of-the-art-in-open-domain","title":"Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize","date":"2018-12-27","arxiv_id":"1812.10757","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-flooding-for-detecting-audio","title":"Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognition","date":"2018-12-25","arxiv_id":"1812.10061","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-collaborative-deep","title":"Privacy-Preserving Collaborative Deep Learning with Unreliable Participants","date":"2018-12-25","arxiv_id":"1812.10113","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speech-recognition-via-segmental","title":"Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching","date":"2018-12-23","arxiv_id":"1812.09323","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-analysis-of-deep-audio-visual","title":"An Empirical Analysis of Deep Audio-Visual Models for Speech Recognition","date":"2018-12-21","arxiv_id":"1812.09336","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-meta-reinforcement-learning-for-1","title":"A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search","date":"2018-12-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"squantizer-simultaneous-learning-for-both","title":"SQuantizer: Simultaneous Learning for Both Sparse and Low-precision Neural Networks","date":"2018-12-20","arxiv_id":"1812.08301","repositories_listed":0,"syntology":null},{"url":null,"slug":"adam-induces-implicit-weight-sparsity-in","title":"Adam Induces Implicit Weight Sparsity in Rectifier Neural Networks","date":"2018-12-19","arxiv_id":"1812.08119","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-voice-query-recognition-using","title":"Streaming Voice Query Recognition using Causal Convolutional Recurrent Neural Networks","date":"2018-12-19","arxiv_id":"1812.07754","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-topic-identification-in-humanhuman","title":"Multiple topic identification in human/human conversations","date":"2018-12-18","arxiv_id":"1812.07207","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-meta-reinforcement-learning-for","title":"A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search","date":"2018-12-17","arxiv_id":"1812.07995","repositories_listed":0,"syntology":null},{"url":"/paper/fully-convolutional-speech-recognition","slug":"fully-convolutional-speech-recognition","title":"Fully Convolutional Speech Recognition","date":"2018-12-17","arxiv_id":"1812.06864","repositories_listed":0,"syntology":null},{"url":null,"slug":"persian-phonemes-recognition-using-ppnet","title":"The Recognition Of Persian Phonemes Using PPNet","date":"2018-12-17","arxiv_id":"1812.08600","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-data-normalization-on-deep-neural","title":"Impact of Data Normalization on Deep Neural Network for Time Series Forecasting","date":"2018-12-13","arxiv_id":"1812.05519","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-rnn-design-optimization-for-efficient","title":"E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs","date":"2018-12-12","arxiv_id":"1812.07106","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-language-model-adaptation-for-spoken","title":"Scalable language model adaptation for spoken dialogue systems","date":"2018-12-11","arxiv_id":"1812.04647","repositories_listed":0,"syntology":null},{"url":null,"slug":"to-reverse-the-gradient-or-not-an-empirical","title":"To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition","date":"2018-12-09","arxiv_id":"1812.03483","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ustc-nel-speech-translation-system-at","title":"The USTC-NEL Speech Translation system at IWSLT 2018","date":"2018-12-06","arxiv_id":"1812.02455","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-contextual-speech-recognition","title":"End-to-end contextual speech recognition using class language models and a token passing decoder","date":"2018-12-05","arxiv_id":"1812.02142","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-tuning-tensorflow-threading-model-for","title":"Auto-tuning TensorFlow Threading Model for CPU Backend","date":"2018-12-04","arxiv_id":"1812.01665","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-neural-network-based-speech-recognition","title":"Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"jie-he-jian-bie-shi-xun-lian-yu-mo-xing-he","title":"結合鑑別式訓練與模型合併於半監督式語音辨識之研究 (Leveraging Discriminative Training and Model Combination for Semi-supervised Speech Recognition)","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"shi-yong-chang-duan-qi-ji-yi-lei-shen-jing","title":"使用長短期記憶類神經網路建構中文語音辨識器之研究 (A Study on Mandarin Speech Recognition using Long Short- Term Memory Neural Network)","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustics-guided-evaluation-age-a-new-measure","title":"Acoustics-guided evaluation (AGE): a new measure for estimating performance of speech enhancement algorithms for robust ASR","date":"2018-11-28","arxiv_id":"1811.11517","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-inductive-bias-of-word-character-level","title":"On the Inductive Bias of Word-Character-Level Multi-Task Learning for Speech Recognition","date":"2018-11-28","arxiv_id":"1812.02308","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-non-uniform-quantizer-for-quantized","title":"Efficient non-uniform quantizer for quantized neural network targeting reconfigurable hardware","date":"2018-11-27","arxiv_id":"1811.10869","repositories_listed":0,"syntology":null},{"url":null,"slug":"bytes-are-all-you-need-end-to-end","title":"Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes","date":"2018-11-22","arxiv_id":"1811.09021","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-depression-symptom-severity-from","title":"Measuring Depression Symptom Severity from Spoken Language and 3D Facial Expressions","date":"2018-11-21","arxiv_id":"1811.08592","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-with-quaternion-neural","title":"Speech recognition with quaternion neural networks","date":"2018-11-21","arxiv_id":"1811.09678","repositories_listed":0,"syntology":null},{"url":null,"slug":"west-word-encoded-sequence-transducers","title":"WEST: Word Encoded Sequence Transducers","date":"2018-11-20","arxiv_id":"1811.08417","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-voice-controlled-e-commerce-web-application","title":"A Voice Controlled E-Commerce Web Application","date":"2018-11-16","arxiv_id":"1811.09688","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-online-attention-based-model-for-speech","title":"An Online Attention-based Model for Speech Recognition","date":"2018-11-13","arxiv_id":"1811.05247","repositories_listed":0,"syntology":null},{"url":null,"slug":"corpus-phonetics-tutorial","title":"Corpus Phonetics Tutorial","date":"2018-11-13","arxiv_id":"1811.05553","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-rnn-transducer-for-chinese-speech","title":"Exploring RNN-Transducer for Chinese Speech Recognition","date":"2018-11-13","arxiv_id":"1811.05097","repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-attention-for-end-to-end-audio","title":"Modality Attention for End-to-End Audio-visual Speech Recognition","date":"2018-11-13","arxiv_id":"1811.05250","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-deep-cnn-based-utterance-embeddings","title":"Analyzing deep CNN-based utterance embeddings for acoustic model adaptation","date":"2018-11-12","arxiv_id":"1811.04708","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-encoder-multi-resolution-framework-for","title":"Multi-encoder multi-resolution framework for end-to-end speech recognition","date":"2018-11-12","arxiv_id":"1811.04897","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-level-knowledge-distillation-for","title":"Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition","date":"2018-11-12","arxiv_id":"1811.04531","repositories_listed":0,"syntology":null},{"url":null,"slug":"stream-attention-based-multi-array-end-to-end","title":"Stream attention-based multi-array end-to-end speech recognition","date":"2018-11-12","arxiv_id":"1811.04903","repositories_listed":0,"syntology":null},{"url":null,"slug":"vectorization-of-hypotheses-and-speech-for","title":"Vectorization of hypotheses and speech for faster beam search in encoder decoder-based speech recognition","date":"2018-11-12","arxiv_id":"1811.04568","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-end-to-end-speech-recognition-with","title":"Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling","date":"2018-11-10","arxiv_id":"1811.04284","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-based-speech","title":"Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition","date":"2018-11-10","arxiv_id":"1811.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"confusion2vec-towards-enriching-vector-space","title":"Confusion2Vec: Towards Enriching Vector Space Word Representations with Representational Ambiguities","date":"2018-11-08","arxiv_id":"1811.03199","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-learning-with-attention-based","title":"Few-shot learning with attention-based sequence-to-sequence models","date":"2018-11-08","arxiv_id":"1811.03519","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-multilingual-sequence-to-sequence","title":"Analysis of Multilingual Sequence-to-Sequence speech recognition systems","date":"2018-11-07","arxiv_id":"1811.03451","repositories_listed":0,"syntology":null},{"url":null,"slug":"cnn-based-multichannel-end-to-end-speech","title":"CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments","date":"2018-11-07","arxiv_id":"1811.02735","repositories_listed":0,"syntology":null},{"url":null,"slug":"rnnfast-an-accelerator-for-recurrent-neural","title":"RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory","date":"2018-11-07","arxiv_id":"1812.07609","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fluent-translations-from-disfluent","title":"Towards Fluent Translations from Disfluent Speech","date":"2018-11-07","arxiv_id":"1811.03189","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-training-of-rnnlms-with-the","title":"Discriminative training of RNNLMs with the average word error criterion","date":"2018-11-06","arxiv_id":"1811.02528","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-neural-network-architecture-in","title":"Hierarchical Neural Network Architecture In Keyword Spotting","date":"2018-11-06","arxiv_id":"1811.02320","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-integration-based-on-memory","title":"Language model integration based on memory control for sequence to sequence speech recognition","date":"2018-11-06","arxiv_id":"1811.02162","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconstructing-speech-stimuli-from-human","title":"Reconstructing Speech Stimuli From Human Auditory Cortex Activity Using a WaveNet Approach","date":"2018-11-06","arxiv_id":"1811.02694","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-monaural-multi-speaker-asr-system","title":"End-to-End Monaural Multi-speaker ASR System without Pretraining","date":"2018-11-05","arxiv_id":"1811.02062","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-weakly-supervised-data-to-improve","title":"Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation","date":"2018-11-05","arxiv_id":"1811.02050","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-marchex-2018-english-conversational","title":"The Marchex 2018 English Conversational Telephone Speech Recognition System","date":"2018-11-05","arxiv_id":"1811.02058","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-black-box-attacks-for-automatic","title":"Adversarial Black-Box Attacks on Automatic Speech Recognition Systems using Multi-Objective Evolutionary Optimization","date":"2018-11-04","arxiv_id":"1811.01312","repositories_listed":0,"syntology":null},{"url":null,"slug":"pushing-the-boundaries-of-audiovisual-word","title":"Pushing the boundaries of audiovisual word recognition using Residual Networks and LSTMs","date":"2018-11-03","arxiv_id":"1811.01194","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-of-end-to-end-speech","title":"Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model","date":"2018-11-02","arxiv_id":"1811.00787","repositories_listed":0,"syntology":null},{"url":null,"slug":"cycle-consistency-training-for-end-to-end","title":"Cycle-consistency training for end-to-end speech recognition","date":"2018-11-02","arxiv_id":"1811.01690","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-robustness-of-speech","title":"Improving the Robustness of Speech Translation","date":"2018-11-02","arxiv_id":"1811.00728","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-neural-speech-recognition-systems","title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation","date":"2018-11-02","arxiv_id":"1811.00707","repositories_listed":0,"syntology":null},{"url":null,"slug":"introspection-for-convolutional-automatic","title":"Introspection for convolutional automatic speech recognition","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sisyphus-a-workflow-manager-designed-for","title":"Sisyphus, a Workflow Manager Designed for Machine Translation and Automatic Speech Recognition","date":"2018-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tropical-modeling-of-weighted-transducer","title":"Tropical Modeling of Weighted Transducer Algorithms on Graphs","date":"2018-11-01","arxiv_id":"1811.00573","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-feedback-loss-in-speech-chain","title":"End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator","date":"2018-10-31","arxiv_id":"1810.13107","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-dimensional-bottleneck-features-for-on","title":"Low-Dimensional Bottleneck Features for On-Device Continuous Speech Recognition","date":"2018-10-31","arxiv_id":"1811.00006","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-end-to-end-code-switching-speech","title":"Towards End-to-End Code-Switching Speech Recognition","date":"2018-10-31","arxiv_id":"1810.13091","repositories_listed":0,"syntology":null},{"url":null,"slug":"almost-unsupervised-speech-recognition-with","title":"Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data","date":"2018-10-30","arxiv_id":"1810.12566","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-end-to-end-automatic-code-switching","title":"Towards End-to-end Automatic Code-Switching Speech Recognition","date":"2018-10-30","arxiv_id":"1810.12620","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-cnn-resbilstm-ctc-an-end-to-end","title":"Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition","date":"2018-10-29","arxiv_id":"1810.12001","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-speech-recognition-with-difficult","title":"Contextual Speech Recognition with Difficult Negative Training Examples","date":"2018-10-29","arxiv_id":"1810.12170","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypergraph-based-semi-supervised-learning","title":"Hypergraph based semi-supervised learning algorithms applied to speech recognition problem: a novel approach","date":"2018-10-28","arxiv_id":"1810.12743","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuron-activation-profiles-for-interpreting","title":"Neuron Activation Profiles for Interpreting Convolutional Speech Recognition Models","date":"2018-10-26","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-speech-enhancement-in-unseen","title":"Scaling Speech Enhancement in Unseen Environments with Noise Embeddings","date":"2018-10-26","arxiv_id":"1810.12757","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-selective-beamformer-with-keyword","title":"Speaker Selective Beamformer with Keyword Mask Estimation","date":"2018-10-25","arxiv_id":"1810.10727","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-sequence-to-sequence-mapping","title":"Tackling Sequence to Sequence Mapping Problems with Neural Networks","date":"2018-10-25","arxiv_id":"1810.10802","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-memad-submission-to-the-iwslt-2018-speech","title":"The MeMAD Submission to the IWSLT 2018 Speech Translation Task","date":"2018-10-24","arxiv_id":"1810.10320","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-generative-acoustic-model-for","title":"A Deep Generative Acoustic Model for Compositional Automatic Speech Recognition","date":"2018-10-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-at-scale","title":"Language Modeling at Scale","date":"2018-10-23","arxiv_id":"1810.10045","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-model-training-for","title":"Semi-supervised acoustic model training for speech with code-switching","date":"2018-10-23","arxiv_id":"1810.09699","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-analysis-on-attention-models","title":"A comprehensive analysis on attention models","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cycle-consistent-gan-front-end-to-improve-asr","title":"Cycle-Consistent GAN Front-End to Improve ASR Robustness to Perturbed Speech","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"how-transferable-are-features-in","title":"How transferable are features in convolutional neural network acoustic models across languages?","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-speech-enhancement-with-the-wave-u-1","title":"Improved Speech Enhancement with the Wave-U-Net","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learned-in-speech-recognition-contextual-1","title":"Learned in Speech Recognition: Contextual Acoustic Word Embeddings","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-inductive-bias-of-word-character-level-1","title":"On the Inductive Bias of Word-Character-Level Multi-Task Learning for Speech Recognition","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"proactive-security-embedded-ai-solution-for","title":"Proactive Security: Embedded AI Solution for Violent and Abusive Speech Recognition","date":"2018-10-22","arxiv_id":"1810.09431","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-domain-adaptation-by-augmented-cyclic","title":"Robust Domain Adaptation By Augmented Cyclic Adversarial Learning","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speech-command-recognition-using-label","title":"ROBUST SPEECH COMMAND RECOGNITION USING LABEL-DRIVEN TIME-FREQUENCY MASKING","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"ebaf991e59bd4f901479010cc2ecdf35a8f8537646f4e2c237fc9b31df59f18b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}