{"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/papers/48","list_of":"/task/speech-recognition","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":48,"pages_in_order":65,"rows_per_page":100,"rows":[4701,4800],"of":6433,"counts":{"archive_papers_tagged":6433,"with_a_code_link":1373,"where_syntology_ran_a_sample":196,"not_listed_spam_title":0,"listed":6433,"listed_where_code_ran":196,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":162,"every_run_a_failure_of_syntologys_instrument":34,"listed_with_a_run_with_no_instrument_failure":162,"listed_every_run_a_failure_of_syntologys_instrument":34,"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","prev":"/task/speech-recognition/papers/47","next":"/task/speech-recognition/papers/49","papers":[{"url":null,"slug":"an-investigation-into-on-device","title":"An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models","date":"2019-09-14","arxiv_id":"1909.06678","repositories_listed":0,"syntology":null},{"url":null,"slug":"current-challenges-in-spoken-dialogue-systems","title":"Current Challenges in Spoken Dialogue Systems and Why They Are Critical for Those Living with Dementia","date":"2019-09-14","arxiv_id":"1909.06644","repositories_listed":0,"syntology":null},{"url":null,"slug":"ffdl-a-flexible-multi-tenant-deep-learning","title":"FfDL : A Flexible Multi-tenant Deep Learning Platform","date":"2019-09-14","arxiv_id":"1909.06526","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-source-channel-and-attention","title":"Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition","date":"2019-09-14","arxiv_id":"1909.06614","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-out-of-task-data-for-end-to-end","title":"Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade","date":"2019-09-14","arxiv_id":"1909.06515","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognition-of-handwritten-digit-using","title":"Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers","date":"2019-09-12","arxiv_id":"1909.08490","repositories_listed":0,"syntology":null},{"url":null,"slug":"eligibility-traces-provide-a-data-inspired","title":"Eligibility traces provide a data-inspired alternative to backpropagation through time","date":"2019-09-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-multilingual-speech-recognition","title":"Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model","date":"2019-09-11","arxiv_id":"1909.05330","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-teaching-networks","title":"Self-Teaching Networks","date":"2019-09-09","arxiv_id":"1909.04157","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-based-modeling-of-phonetic","title":"Neural Network-Based Modeling of Phonetic Durations","date":"2019-09-06","arxiv_id":"1909.03030","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-and-perceptually-motivated","title":"An efficient and perceptually motivated auditory neural encoding and decoding algorithm for spiking neural networks","date":"2019-09-03","arxiv_id":"1909.01302","repositories_listed":0,"syntology":null},{"url":null,"slug":"avaya-conversational-intelligence-a-real-time","title":"Avaya Conversational Intelligence: A Real-Time System for Spoken Language Understanding in Human-Human Call Center Conversations","date":"2019-09-02","arxiv_id":"1909.02851","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-probabilistic-approach-for-confidence","title":"A Probabilistic Approach for Confidence Scoring in Speech Recognition","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dialect-specific-models-for-automatic-speech","title":"Dialect-Specific Models for Automatic Speech Recognition of African American Vernacular English","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"garnishing-a-phonetic-dictionary-for-asr","title":"Garnishing a phonetic dictionary for ASR intake","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"human-informed-speakers-and-interpreters","title":"Human-Informed Speakers and Interpreters Analysis in the WAW Corpus and an Automatic Method for Calculating Interpreters' D\\'ecalage","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"motivations-challenges-and-perspectives-for","title":"Motivations, challenges, and perspectives for the development of an Automatic Speech Recognition System for the under-resourced Ngiemboon Language","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-language-model-for-tunisian-dialect","title":"Semantic Language Model for Tunisian Dialect","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ambiguous-world-of-emotion-representation","title":"The Ambiguous World of Emotion Representation","date":"2019-09-01","arxiv_id":"1909.00360","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-accurate-text-verbalization-for-asr","title":"Towards Accurate Text Verbalization for ASR Based on Audio Alignment","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-and-mars-a-connection","title":"Estimation of a function of low local dimensionality by deep neural networks","date":"2019-08-29","arxiv_id":"1908.11140","repositories_listed":0,"syntology":null},{"url":null,"slug":"deploying-technology-to-save-endangered","title":"Deploying Technology to Save Endangered Languages","date":"2019-08-23","arxiv_id":"1908.08971","repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-representation-in-french-broadcast","title":"Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance","date":"2019-08-23","arxiv_id":"1908.08717","repositories_listed":0,"syntology":null},{"url":null,"slug":"masr-a-modular-accelerator-for-sparse-rnns","title":"MASR: A Modular Accelerator for Sparse RNNs","date":"2019-08-23","arxiv_id":"1908.08976","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-reinforcing-unsupervised-matching","title":"Self-reinforcing Unsupervised Matching","date":"2019-08-23","arxiv_id":"1909.04138","repositories_listed":0,"syntology":null},{"url":null,"slug":"190807888","title":"Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition","date":"2019-08-21","arxiv_id":"1908.07888","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-and-accessibility-a-discussion-of-ethical","title":"AI and Accessibility: A Discussion of Ethical Considerations","date":"2019-08-21","arxiv_id":"1908.08939","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-staged-acoustic-modeling-adaption-for","title":"Two-Staged Acoustic Modeling Adaption for Robust Speech Recognition by the Example of German Oral History Interviews","date":"2019-08-19","arxiv_id":"1908.06709","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-multi-speaker-speech-recognition","title":"End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning","date":"2019-08-13","arxiv_id":"1908.04737","repositories_listed":0,"syntology":null},{"url":"/paper/ims-speech-a-speech-to-text-tool","slug":"ims-speech-a-speech-to-text-tool","title":"IMS-Speech: A Speech to Text Tool","date":"2019-08-13","arxiv_id":"1908.04743","repositories_listed":0,"syntology":null},{"url":null,"slug":"space-time-error-estimates-for-deep-neural","title":"Space-time error estimates for deep neural network approximations for differential equations","date":"2019-08-11","arxiv_id":"1908.03833","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-stemming-based-language-model","title":"Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription","date":"2019-08-10","arxiv_id":"1908.03734","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenging-the-boundaries-of-speech","title":"Challenging the Boundaries of Speech Recognition: The MALACH Corpus","date":"2019-08-09","arxiv_id":"1908.03455","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-cross-lingual-speaker-and-phonetic","title":"Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling","date":"2019-08-09","arxiv_id":"1908.03538","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-semi-supervised-training-through-a","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","date":"2019-08-08","arxiv_id":"1908.05227","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-noisy-inputs-for-question","title":"Mitigating Noisy Inputs for Question Answering","date":"2019-08-08","arxiv_id":"1908.02914","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-accurate-capitalization-and","title":"Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging","date":"2019-08-07","arxiv_id":"1908.02404","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-text-independent-speaker","title":"An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network","date":"2019-08-06","arxiv_id":"1908.02612","repositories_listed":0,"syntology":null},{"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":"multilingual-speech-recognition-with-corpus","title":"Multilingual Speech Recognition with Corpus Relatedness Sampling","date":"2019-08-02","arxiv_id":"1908.01060","repositories_listed":0,"syntology":null},{"url":null,"slug":"santlr-speech-annotation-toolkit-for-low","title":"SANTLR: Speech Annotation Toolkit for Low Resource Languages","date":"2019-08-02","arxiv_id":"1908.01067","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-joint-acoustic-phonetic-word","title":"Learning Joint Acoustic-Phonetic Word Embeddings","date":"2019-08-01","arxiv_id":"1908.00493","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-for-tigrinya-language","title":"Speech Recognition for Tigrinya language Using Deep Neural Network Approach","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-automated-content-feedback-generation","title":"Toward Automated Content Feedback Generation for Non-native Spontaneous Speech","date":"2019-08-01","arxiv_id":null,"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":"multi-frame-cross-entropy-training-for","title":"Multi-Frame Cross-Entropy Training for Convolutional Neural Networks in Speech Recognition","date":"2019-07-29","arxiv_id":"1907.13121","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":"a-comparison-of-deep-learning-performances","title":"A comparison of Deep Learning performances with other machine learning algorithms on credit scoring unbalanced data","date":"2019-07-25","arxiv_id":"1907.12363","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-attention-end-to-end-asr-for-two-party","title":"Cross-Attention End-to-End ASR for Two-Party Conversations","date":"2019-07-24","arxiv_id":"1907.10726","repositories_listed":0,"syntology":null},{"url":null,"slug":"2d-ctc-for-scene-text-recognition","title":"2D-CTC for Scene Text Recognition","date":"2019-07-23","arxiv_id":"1907.09705","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-to-address-candidate-generation","title":"Deep Learning to Address Candidate Generation and Cold Start Challenges in Recommender Systems: A Research Survey","date":"2019-07-17","arxiv_id":"1907.08674","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-neural-network-architectures","title":"Comparison of Neural Network Architectures for Spectrum Sensing","date":"2019-07-15","arxiv_id":"1907.07321","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":"investigation-on-n-gram-approximated-rnnlms","title":"Investigation on N-gram Approximated RNNLMs for Recognition of Morphologically Rich Speech","date":"2019-07-15","arxiv_id":"1907.06407","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-spelling-from-teachers-transferring","title":"Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition","date":"2019-07-13","arxiv_id":"1907.06017","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":"/paper/multi-layer-attention-mechanism-for-speech","slug":"multi-layer-attention-mechanism-for-speech","title":"Multi-layer Attention Mechanism for Speech Keyword Recognition","date":"2019-07-10","arxiv_id":"1907.04536","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-reverberant-speech-training-using","title":"Improving Reverberant Speech Training Using Diffuse Acoustic Simulation","date":"2019-07-09","arxiv_id":"1907.03988","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":"m3d-gan-multi-modal-multi-domain-translation","title":"M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention","date":"2019-07-09","arxiv_id":"1907.04378","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":"transfer-learning-from-audio-visual-grounding","title":"Transfer Learning from Audio-Visual Grounding to Speech Recognition","date":"2019-07-09","arxiv_id":"1907.04355","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":"toward-fairness-in-ai-for-people-with","title":"Toward Fairness in AI for People with Disabilities: A Research Roadmap","date":"2019-07-04","arxiv_id":"1907.02227","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":"an-adaptable-task-oriented-dialog-system-for","title":"An adaptable task-oriented dialog system for stand-alone embedded devices","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"apport-de-l-adaptation-automatique-des-mod","title":"Apport de l'adaptation automatique des mod\\`eles de langage pour la reconnaissance de la parole: \\'evaluation qualitative extrins\\`eque dans un contexte de traitement de cours magistraux (Contribution of automatic adaptation of language models for speech recognition : extrinsic qualitative evaluation in a context of educational courses)","date":"2019-07-01","arxiv_id":null,"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":"deep-bayesian-natural-language-processing","title":"Deep Bayesian Natural Language Processing","date":"2019-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-performance-of-end-to-end-asr-on","title":"Improving Performance of End-to-End ASR on Numeric Sequences","date":"2019-07-01","arxiv_id":"1907.01372","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-representations-from-imperfect-time","title":"Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization","date":"2019-07-01","arxiv_id":"1907.01011","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":"gated-embeddings-in-end-to-end-speech","title":"Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion","date":"2019-06-27","arxiv_id":"1906.11604","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":"essence-knowledge-distillation-for-speech","title":"Essence Knowledge Distillation for Speech Recognition","date":"2019-06-26","arxiv_id":"1906.10834","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":"a-winograd-based-integrated-photonics","title":"A Winograd-based Integrated Photonics Accelerator for Convolutional Neural Networks","date":"2019-06-25","arxiv_id":"1906.10487","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-learning-machines-from-atr-to-dna","title":"Machine Learning Construction: implications to cybersecurity","date":"2019-06-24","arxiv_id":"1906.10019","repositories_listed":0,"syntology":null},{"url":null,"slug":"database-meets-deep-learning-challenges-and","title":"Database Meets Deep Learning: Challenges and Opportunities","date":"2019-06-21","arxiv_id":"1906.08986","repositories_listed":0,"syntology":null},{"url":null,"slug":"integration-of-tensorflow-based-acoustic","title":"Integration of TensorFlow based Acoustic Model with Kaldi WFST Decoder","date":"2019-06-21","arxiv_id":"1906.11018","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":"a-simple-and-effective-postprocessing-method","title":"A simple and effective postprocessing method for image classification","date":"2019-06-19","arxiv_id":"1906.07934","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":"on-combining-features-for-single-channel","title":"On combining features for single-channel robust speech recognition in reverberant environments","date":"2019-06-17","arxiv_id":"1906.07299","repositories_listed":0,"syntology":null}],"record_sha256":"108b0e6d6e9b8281df1c7bf6b27f55111d40bc9e666e63fd545c67968790bb4c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}