{"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/papers/26","list_of":"/task/automatic-speech-recognition","task":"Automatic Speech Recognition (ASR)","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":26,"pages_in_order":31,"rows_per_page":100,"rows":[2501,2600],"of":3012,"counts":{"archive_papers_tagged":3012,"with_a_code_link":622,"where_syntology_ran_a_sample":77,"not_listed_spam_title":0,"listed":3012,"listed_where_code_ran":77,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":64,"every_run_a_failure_of_syntologys_instrument":13,"listed_with_a_run_with_no_instrument_failure":64,"listed_every_run_a_failure_of_syntologys_instrument":13,"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","prev":"/task/automatic-speech-recognition/papers/25","next":"/task/automatic-speech-recognition/papers/27","papers":[{"url":null,"slug":"practical-speech-recognition-with-htk","title":"Practical Speech Recognition with HTK","date":"2019-08-06","arxiv_id":"1908.02119","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-over-the-air-adversarial-examples","title":"Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems","date":"2019-08-05","arxiv_id":"1908.01551","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2s-attack-building-dnn-based-voice","title":"V2S attack: building DNN-based voice conversion from automatic speaker verification","date":"2019-08-05","arxiv_id":"1908.01454","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-speech-test-set-of-practice-business","title":"A Speech Test Set of Practice Business Presentations with Additional Relevant Texts","date":"2019-08-02","arxiv_id":"1908.00916","repositories_listed":0,"syntology":null},{"url":null,"slug":"dutongchuan-context-aware-translation-model","title":"DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting","date":"2019-07-30","arxiv_id":"1907.12984","repositories_listed":0,"syntology":null},{"url":null,"slug":"correlation-distance-skip-connection","title":"Correlation Distance Skip Connection Denoising Autoencoder (CDSK-DAE) for Speech Feature Enhancement","date":"2019-07-26","arxiv_id":"1907.11361","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-sequence-to-sequence-voice","title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","date":"2019-07-15","arxiv_id":"1907.07769","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-target-set-reduction-for-end-to","title":"Investigating Target Set Reduction for End-to-End Speech Recognition of Hindi-English Code-Switching Data","date":"2019-07-15","arxiv_id":"1907.08293","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-highly-efficient-distributed-deep-learning","title":"A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition","date":"2019-07-10","arxiv_id":"1907.05701","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-model-optimization-based-on","title":"Acoustic Model Optimization Based On Evolutionary Stochastic Gradient Descent with Anchors for Automatic Speech Recognition","date":"2019-07-10","arxiv_id":"1907.04882","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-mixed-bandwidth-deep-neural","title":"Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition","date":"2019-07-10","arxiv_id":"1907.04887","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-speech-recognition-and-speaker","title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","date":"2019-07-09","arxiv_id":"1907.05337","repositories_listed":0,"syntology":null},{"url":null,"slug":"teach-an-all-rounder-with-experts-in","title":"Teach an all-rounder with experts in different domains","date":"2019-07-09","arxiv_id":"1907.05698","repositories_listed":0,"syntology":null},{"url":null,"slug":"shrinkml-end-to-end-asr-model-compression","title":"ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning","date":"2019-07-08","arxiv_id":"1907.03540","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-low-resource-somali-speech","title":"Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training","date":"2019-07-06","arxiv_id":"1907.03064","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-recognition-with-high-frame","title":"End-to-End Speech Recognition with High-Frame-Rate Features Extraction","date":"2019-07-03","arxiv_id":"1907.01957","repositories_listed":0,"syntology":null},{"url":"/paper/kite-automatic-speech-recognition-for","slug":"kite-automatic-speech-recognition-for","title":"Kite: Automatic speech recognition for unmanned aerial vehicles","date":"2019-07-02","arxiv_id":"1907.01195","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-dirichlet-allocation-based-acoustic","title":"Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition","date":"2019-07-02","arxiv_id":"1907.01302","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-multi-corpora-neural-language-models","title":"Scalable Multi Corpora Neural Language Models for ASR","date":"2019-07-02","arxiv_id":"1907.01677","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-cross-language-intelligibility","title":"Automated Cross-language Intelligibility Analysis of Parkinson's Disease Patients Using Speech Recognition Technologies","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-lattice-free-and-lattice-based","title":"Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR","date":"2019-07-01","arxiv_id":"1907.01409","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-utility-of-visual-context-in","title":"Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions","date":"2019-06-30","arxiv_id":"1907.00477","repositories_listed":0,"syntology":null},{"url":null,"slug":"auxiliary-interference-speaker-loss-for","title":"Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition","date":"2019-06-26","arxiv_id":"1906.10876","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-size-does-not-fit-all-quantifying-and","title":"One Size Does Not Fit All: Quantifying and Exposing the Accuracy-Latency Trade-off in Machine Learning Cloud Service APIs via Tolerance Tiers","date":"2019-06-26","arxiv_id":"1906.11307","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-span-acoustic-modelling-using-raw","title":"Multi-Span Acoustic Modelling using Raw Waveform Signals","date":"2019-06-21","arxiv_id":"1906.11047","repositories_listed":0,"syntology":null},{"url":null,"slug":"phoneme-based-contextualization-for-cross","title":"Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models","date":"2019-06-21","arxiv_id":"1906.09292","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switching-detection-using-asr-generated","title":"Code-Switching Detection Using ASR-Generated Language Posteriors","date":"2019-06-19","arxiv_id":"1906.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-graph-decoding-for-code-switching-asr","title":"Multi-Graph Decoding for Code-Switching ASR","date":"2019-06-18","arxiv_id":"1906.07523","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-speech-recognition-with-no-speech","title":"Advancing Speech Recognition With No Speech Or With Noisy Speech","date":"2019-06-17","arxiv_id":"1906.08871","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-training-for-multilingual","title":"Adversarial Training for Multilingual Acoustic Modeling","date":"2019-06-17","arxiv_id":"1906.07093","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-stream-end-to-end-speech-recognition","title":"Multi-Stream End-to-End Speech Recognition","date":"2019-06-17","arxiv_id":"1906.08041","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-to-h-space-encoder-for-speech","title":"Real to H-space Encoder for Speech Recognition","date":"2019-06-17","arxiv_id":"1906.08043","repositories_listed":0,"syntology":null},{"url":null,"slug":"cumulative-adaptation-for-blstm-acoustic","title":"Cumulative Adaptation for BLSTM Acoustic Models","date":"2019-06-14","arxiv_id":"1906.06207","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-bidirectional-transformer-for","title":"Learning Video Representations using Contrastive Bidirectional Transformer","date":"2019-06-13","arxiv_id":"1906.05743","repositories_listed":0,"syntology":null},{"url":null,"slug":"lattice-transformer-for-speech-translation","title":"Lattice Transformer for Speech Translation","date":"2019-06-13","arxiv_id":"1906.05551","repositories_listed":0,"syntology":null},{"url":null,"slug":"190600579","title":"Listening while Speaking and Visualizing: Improving ASR through Multimodal Chain","date":"2019-06-03","arxiv_id":"1906.00579","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-user-study-to-compare-two-conversational","title":"A user study to compare two conversational assistants designed for people with hearing impairments","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-de-identification-a-new-entity-1","title":"Audio De-identification - a New Entity Recognition Task","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/must-c-a-multilingual-speech-translation","slug":"must-c-a-multilingual-speech-translation","title":"MuST-C: a Multilingual Speech Translation Corpus","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"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":"spatialnet-a-declarative-resource-for-spatial","title":"SpatialNet: A Declarative Resource for Spatial Relations","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":"ai-pipeline-bringing-ai-to-you-end-to-end","title":"Bonseyes AI Pipeline -- bringing AI to you. End-to-end integration of data, algorithms and deployment tools","date":"2019-01-15","arxiv_id":"1901.05049","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}],"record_sha256":"c661fabf1ded38e79df81122a18dd40f921db6b3dd9ab60a72c3dc4e6d9f61e9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}