{"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/automatic-speech-recognition-2/papers/29","list_of":"/task/automatic-speech-recognition-2","task":"Automatic 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":29,"pages_in_order":32,"rows_per_page":100,"rows":[2801,2900],"of":3174,"counts":{"archive_papers_tagged":3174,"with_a_code_link":677,"where_syntology_ran_a_sample":79,"not_listed_spam_title":0,"listed":3174,"listed_where_code_ran":79,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":62,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":62,"listed_every_run_a_failure_of_syntologys_instrument":17,"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/automatic-speech-recognition-2","prev":"/task/automatic-speech-recognition-2/papers/28","next":"/task/automatic-speech-recognition-2/papers/30","papers":[{"url":null,"slug":"overcoming-the-bottleneck-in-traditional","title":"Overcoming the bottleneck in traditional assessments of verbal memory: Modeling human ratings and classifying clinical group membership","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"building-and-evaluation-of-a-real-room","title":"Building and Evaluation of a Real Room Impulse Response Dataset","date":"2019-05-30","arxiv_id":"1811.06795","repositories_listed":0,"syntology":null},{"url":null,"slug":"190601496","title":"Regularization Advantages of Multilingual Neural Language Models for Low Resource Domains","date":"2019-05-29","arxiv_id":"1906.01496","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulatory-and-bottleneck-features-for","title":"Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech","date":"2019-05-16","arxiv_id":"1905.06533","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-sentence-scoring-method-using","title":"Effective Sentence Scoring Method using Bidirectional Language Model for Speech Recognition","date":"2019-05-16","arxiv_id":"1905.06655","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-independent-speech-driven-visual","title":"Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models","date":"2019-05-15","arxiv_id":"1905.06860","repositories_listed":0,"syntology":null},{"url":null,"slug":"almost-unsupervised-text-to-speech-and","title":"Almost Unsupervised Text to Speech and Automatic Speech Recognition","date":"2019-05-13","arxiv_id":"1905.06791","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-contrastive-learning-based-deep","title":"Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification","date":"2019-05-11","arxiv_id":"1905.04554","repositories_listed":0,"syntology":null},{"url":null,"slug":"190503500","title":"Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech","date":"2019-05-09","arxiv_id":"1905.03500","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-adversarial-perturbations-for","title":"Universal Adversarial Perturbations for Speech Recognition Systems","date":"2019-05-09","arxiv_id":"1905.03828","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hardware-oriented-and-memory-efficient","title":"A Hardware-Oriented and Memory-Efficient Method for CTC Decoding","date":"2019-05-08","arxiv_id":"1905.03175","repositories_listed":0,"syntology":null},{"url":null,"slug":"english-broadcast-news-speech-recognition-by","title":"English Broadcast News Speech Recognition by Humans and Machines","date":"2019-04-30","arxiv_id":"1904.13258","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-sequence-to-sequence-asr","slug":"self-supervised-sequence-to-sequence-asr","title":"Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text","date":"2019-04-30","arxiv_id":"1905.01152","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-speaker-adaptation","title":"Adversarial Speaker Adaptation","date":"2019-04-29","arxiv_id":"1904.12407","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentive-adversarial-learning-for-domain","title":"Attentive Adversarial Learning for Domain-Invariant Training","date":"2019-04-28","arxiv_id":"1904.12400","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-domain-multi-channel-acoustic","title":"Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition","date":"2019-04-28","arxiv_id":"1903.05299","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-geometry-spatial-acoustic-modeling-for","title":"Multi-Geometry Spatial Acoustic Modeling for Distant Speech Recognition","date":"2019-04-28","arxiv_id":"1903.06539","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-tolerance-of-neural-machine","title":"Assessing the Tolerance of Neural Machine Translation Systems Against Speech Recognition Errors","date":"2019-04-24","arxiv_id":"1904.10997","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-interactions-in-autonomous","title":"Natural Language Interactions in Autonomous Vehicles: Intent Detection and Slot Filling from Passenger Utterances","date":"2019-04-23","arxiv_id":"1904.10500","repositories_listed":0,"syntology":null},{"url":null,"slug":"dry-focus-and-transcribe-end-to-end","title":"An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions","date":"2019-04-19","arxiv_id":"1904.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"tts-skins-speaker-conversion-via-asr","title":"TTS Skins: Speaker Conversion via ASR","date":"2019-04-18","arxiv_id":"1904.08983","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-task-learning-framework-for","title":"A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition","date":"2019-04-17","arxiv_id":"1904.08039","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-ctc-posterior-spike-timings-for","title":"Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation","date":"2019-04-17","arxiv_id":"1904.08311","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-sample-mining-for-the-improved","title":"Hard Sample Mining for the Improved Retraining of Automatic Speech Recognition","date":"2019-04-17","arxiv_id":"1904.08031","repositories_listed":0,"syntology":null},{"url":null,"slug":"stc-speaker-recognition-systems-for-the","title":"STC Speaker Recognition Systems for the VOiCES From a Distance Challenge","date":"2019-04-12","arxiv_id":"1904.06093","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-deep-learning-strategies-for","title":"Distributed Deep Learning Strategies For Automatic Speech Recognition","date":"2019-04-10","arxiv_id":"1904.04956","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-monitoring-for-end-to-end-speech","title":"Performance Monitoring for End-to-End Speech Recognition","date":"2019-04-09","arxiv_id":"1904.04896","repositories_listed":0,"syntology":null},{"url":null,"slug":"constrained-output-embeddings-for-end-to-end","title":"Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data","date":"2019-04-08","arxiv_id":"1904.03802","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-methods-for-the-automatic-detection","title":"Exploring Methods for the Automatic Detection of Errors in Manual Transcription","date":"2019-04-08","arxiv_id":"1904.04294","repositories_listed":0,"syntology":null},{"url":"/paper/token-level-ensemble-distillation-for","slug":"token-level-ensemble-distillation-for","title":"Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion","date":"2019-04-06","arxiv_id":"1904.03446","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-asr-on-alzheimers-disease-detection","title":"Impact of ASR on Alzheimer's Disease Detection: All Errors are Equal, but Deletions are More Equal than Others","date":"2019-04-02","arxiv_id":"1904.01684","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustically-grounded-word-embeddings-for","title":"Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition","date":"2019-03-29","arxiv_id":"1903.12306","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-acoustic-prosodic-cues-for-word","title":"Modeling Acoustic-Prosodic Cues for Word Importance Prediction in Spoken Dialogues","date":"2019-03-28","arxiv_id":"1903.12238","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speech-enhancement-based-on","title":"Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition","date":"2019-03-22","arxiv_id":"1903.09341","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-de-identification-a-new-entity","title":"Audio De-identification: A New Entity Recognition Task","date":"2019-03-17","arxiv_id":"1903.07037","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-assessment-of-spoken-language","title":"Automatic assessment of spoken language proficiency of non-native children","date":"2019-03-15","arxiv_id":"1903.06409","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-between-monaural-speech","title":"Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling","date":"2019-03-11","arxiv_id":"1903.04567","repositories_listed":0,"syntology":null},{"url":null,"slug":"singing-voice-conversion-with-non-parallel","title":"Singing voice conversion with non-parallel data","date":"2019-03-11","arxiv_id":"1903.04124","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-with-no-speech-or-with","title":"Speech Recognition with no speech or with noisy speech","date":"2019-03-02","arxiv_id":"1903.00739","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-neural-based-dialog-act","title":"Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions","date":"2019-02-28","arxiv_id":"1902.11060","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-end-to-end-speech-recognition","title":"Incorporating End-to-End Speech Recognition Models for Sentiment Analysis","date":"2019-02-28","arxiv_id":"1902.11245","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-neural-online-source-separation-counting","title":"All-neural online source separation, counting, and diarization for meeting analysis","date":"2019-02-21","arxiv_id":"1902.07881","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-attention-aligner-a-latency-control-end","title":"Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hopping","date":"2019-02-18","arxiv_id":"1902.06450","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-robot-speech-recognition-using","title":"Enhanced Robot Speech Recognition Using Biomimetic Binaural Sound Source Localization","date":"2019-02-13","arxiv_id":"1902.05446","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-multi-task-learning-to-improve-the","title":"Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models","date":"2019-02-02","arxiv_id":"1902.01951","repositories_listed":0,"syntology":null},{"url":null,"slug":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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},{"url":null,"slug":"targeted-adversarial-examples-for-black-box-1","title":"Targeted Adversarial Examples for Black Box Audio Systems","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"training-neural-speech-recognition-systems-1","title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-and-configurable-audio","title":"Transferable and Configurable Audio Adversarial Attack from Low-Level Features","date":"2018-10-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-textual-and-speech-information-in","title":"Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation","date":"2018-10-17","arxiv_id":"1810.07455","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-with-quaternion-neural-1","title":"Speech Recognition with Quaternion Neural Networks","date":"2018-10-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-word-disambiguation-with-phonogical","title":"Acoustic Word Disambiguation with Phonogical Features in Danish ASR","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-speech-translation-at-apptek","title":"Neural Speech Translation at AppTek","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"research-challenges-in-building-a-voice-based","title":"Research Challenges in Building a Voice-based Artificial Personal Shopper - Position Paper","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"d4ecb332ae3b7173f49a1e39a462f07846c06be78fc1c96de84206f8cd53189b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}