{"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/43","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":43,"pages_in_order":65,"rows_per_page":100,"rows":[4201,4300],"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/42","next":"/task/speech-recognition/papers/44","papers":[{"url":null,"slug":"multimodal-speech-recognition-with","title":"Multimodal Speech Recognition with Unstructured Audio Masking","date":"2020-10-16","arxiv_id":"2010.08642","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-intrusive-speech-intelligibility","title":"Non-intrusive speech intelligibility prediction using automatic speech recognition derived measures","date":"2020-10-16","arxiv_id":"2010.08574","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-end-to-end-speech-recognition","title":"Lightweight End-to-End Speech Recognition from Raw Audio Data Using Sinc-Convolutions","date":"2020-10-15","arxiv_id":"2010.07597","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-spectral-augmentation-for-code","title":"Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification","date":"2020-10-14","arxiv_id":"2010.07130","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-lightweight-speaker-recognition-system","title":"A Lightweight Speaker Recognition System Using Timbre Properties","date":"2020-10-12","arxiv_id":"2010.05502","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-low-resource-code-switched-asr","title":"Improving Low Resource Code-switched ASR using Augmented Code-switched TTS","date":"2020-10-12","arxiv_id":"2010.05549","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-sound-of-silence-in-eeg-cognitive-voice","title":"The \"Sound of Silence\" in EEG -- Cognitive voice activity detection","date":"2020-10-12","arxiv_id":"2010.05497","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-asr-unify-and-improve-streaming-asr-1","title":"Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling","date":"2020-10-12","arxiv_id":"2010.06030","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-clustering-based-method-for-automatic","title":"A Clustering-Based Method for Automatic Educational Video Recommendation Using Deep Face-Features of Lecturers","date":"2020-10-09","arxiv_id":"2010.04676","repositories_listed":0,"syntology":null},{"url":null,"slug":"population-based-training-for-data","title":"Population Based Training for Data Augmentation and Regularization in Speech Recognition","date":"2020-10-08","arxiv_id":"2010.03899","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-and-specaugment-applied-to","title":"Transfer Learning and SpecAugment applied to SSVEP Based BCI Classification","date":"2020-10-08","arxiv_id":"2010.06503","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adversarial-neural-networks-for","title":"Domain Adversarial Neural Networks for Dysarthric Speech Recognition","date":"2020-10-07","arxiv_id":"2010.03623","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-transducer-one-model-unifying","title":"Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition","date":"2020-10-07","arxiv_id":"2010.03192","repositories_listed":0,"syntology":null},{"url":null,"slug":"wer-we-are-and-wer-we-think-we-are","title":"WER we are and WER we think we are","date":"2020-10-07","arxiv_id":"2010.03432","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-deep-neural-networks","title":"Explaining Deep Neural Networks","date":"2020-10-04","arxiv_id":"2010.01496","repositories_listed":0,"syntology":null},{"url":null,"slug":"ji-yu-pin-yin-yue-shu-lian-he-xue-xi-de-yi-yu","title":"基于拼音约束联合学习的汉语语音识别(Chinese Speech Recognition Based on Pinyin Constraint Joint Learning)","date":"2020-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-spoken-language-understanding","title":"End-to-End Spoken Language Understanding Without Full Transcripts","date":"2020-09-30","arxiv_id":"2009.14386","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-design-and-implementation-of-language","title":"The design and implementation of Language Learning Chatbot with XAI using Ontology and Transfer Learning","date":"2020-09-29","arxiv_id":"2009.13984","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-lip-localization-techniques-used","title":"A Study on Lip Localization Techniques used for Lip reading from a Video","date":"2020-09-28","arxiv_id":"2009.13420","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimation-error-analysis-of-deep-learning-on","title":"Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space","date":"2020-09-23","arxiv_id":"2009.11285","repositories_listed":0,"syntology":null},{"url":null,"slug":"fluentnet-end-to-end-detection-of-speech","title":"FluentNet: End-to-End Detection of Speech Disfluency with Deep Learning","date":"2020-09-23","arxiv_id":"2009.11394","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-deep-neural-networks-for","title":"An analysis of deep neural networks for predicting trends in time series data","date":"2020-09-16","arxiv_id":"2009.07943","repositories_listed":0,"syntology":null},{"url":null,"slug":"easyasr-a-distributed-machine-learning","title":"EasyASR: A Distributed Machine Learning Platform for End-to-end Automatic Speech Recognition","date":"2020-09-14","arxiv_id":"2009.06487","repositories_listed":0,"syntology":null},{"url":null,"slug":"monolingual-data-selection-analysis-for","title":"Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-switching Speech Recognition","date":"2020-09-14","arxiv_id":"2006.07094","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-embeddings-using-multi-task","title":"Multi-modal embeddings using multi-task learning for emotion recognition","date":"2020-09-10","arxiv_id":"2009.05019","repositories_listed":0,"syntology":null},{"url":null,"slug":"swp-leaf-net-a-novel-multistage-approach-for","title":"SWP-LeafNET: A novel multistage approach for plant leaf identification based on deep CNN","date":"2020-09-10","arxiv_id":"2009.05139","repositories_listed":0,"syntology":null},{"url":null,"slug":"unmanned-aerial-vehicle-control-through","title":"Unmanned Aerial Vehicle Control Through Domain-based Automatic Speech Recognition","date":"2020-09-09","arxiv_id":"2009.04215","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-architecture-of-online-multi","title":"An End-to-end Architecture of Online Multi-channel Speech Separation","date":"2020-09-07","arxiv_id":"2009.03141","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-spoken-language-understanding-with-rl","title":"Robust Spoken Language Understanding with RL-based Value Error Recovery","date":"2020-09-07","arxiv_id":"2009.03095","repositories_listed":0,"syntology":null},{"url":null,"slug":"silent-speech-interfaces-for-speech","title":"Silent Speech Interfaces for Speech Restoration: A Review","date":"2020-09-04","arxiv_id":"2009.02110","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowing-what-to-listen-to-early-attention-for","title":"Fine-grained Early Frequency Attention for Deep Speaker Representation Learning","date":"2020-09-03","arxiv_id":"2009.01822","repositories_listed":0,"syntology":null},{"url":null,"slug":"voice-conversion-by-cascading-automatic","title":"Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer","date":"2020-09-03","arxiv_id":"2009.01475","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-speech-recognition-with-pitch","title":"Convolutional Speech Recognition with Pitch and Voice Quality Features","date":"2020-09-02","arxiv_id":"2009.01309","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-the-brittleness-of-ai-safety","title":"Estimating the Brittleness of AI: Safety Integrity Levels and the Need for Testing Out-Of-Distribution Performance","date":"2020-09-02","arxiv_id":"2009.00802","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-preliminary-study-on-leveraging-meta","title":"A Preliminary Study on Leveraging Meta Learning Technique for Code-switching Speech Recognition","date":"2020-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hearings-and-mishearings-decrypting-the","title":"Hearings and mishearings: decrypting the spoken word","date":"2020-09-01","arxiv_id":"2009.00429","repositories_listed":0,"syntology":null},{"url":null,"slug":"innovative-pretrained-based-reranking","title":"Innovative Pretrained-based Reranking Language Models for N-best Speech Recognition Lists","date":"2020-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-attention-based-speech-enhancement","title":"Multi-view Attention-based Speech Enhancement Model for Noise-robust Automatic Speech Recognition","date":"2020-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nepali-speech-recognition-using-cnn-gru-and","title":"Nepali Speech Recognition Using CNN, GRU and CTC","date":"2020-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-machine-learning-accelerators","title":"Survey of Machine Learning Accelerators","date":"2020-09-01","arxiv_id":"2009.00993","repositories_listed":0,"syntology":null},{"url":null,"slug":"taiwanese-speech-recognition-based-on-hybrid","title":"Taiwanese Speech Recognition Based on Hybrid Deep Neural Network Architecture","date":"2020-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-rescoring-with-transformer-for","title":"Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition","date":"2020-08-30","arxiv_id":"2008.13093","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimising-ai-training-deployments-using","title":"Optimising AI Training Deployments using Graph Compilers and Containers","date":"2020-08-26","arxiv_id":"2008.11675","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-evolutionary-neural-architecture","title":"A Survey on Evolutionary Neural Architecture Search","date":"2020-08-25","arxiv_id":"2008.10937","repositories_listed":0,"syntology":null},{"url":null,"slug":"aphasic-speech-recognition-using-a-mixture-of","title":"Aphasic Speech Recognition using a Mixture of Speech Intelligibility Experts","date":"2020-08-25","arxiv_id":"2008.10788","repositories_listed":0,"syntology":null},{"url":null,"slug":"learned-transferable-architectures-can","title":"Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition","date":"2020-08-25","arxiv_id":"2008.11589","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-tail-performance-of-a-deliberation","title":"Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus","date":"2020-08-24","arxiv_id":"2008.10491","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-semiotics","title":"Machine Semiotics","date":"2020-08-24","arxiv_id":"2008.10522","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-utterance-language-models-with-acoustic","title":"Cross-Utterance Language Models with Acoustic Error Sampling","date":"2020-08-19","arxiv_id":"2009.01008","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-real-time-robot-based-auxiliary-system-for","title":"A Real-time Robot-based Auxiliary System for Risk Evaluation of COVID-19 Infection","date":"2020-08-18","arxiv_id":"2008.07695","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-to-semantics-improve-asr-and-nlu","title":"Speech To Semantics: Improve ASR and NLU Jointly via All-Neural Interfaces","date":"2020-08-14","arxiv_id":"2008.06173","repositories_listed":0,"syntology":null},{"url":null,"slug":"conv-transformer-transducer-low-latency-low","title":"Conv-Transformer Transducer: Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition","date":"2020-08-13","arxiv_id":"2008.05750","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-transfer-learning-for-low","title":"Large-scale Transfer Learning for Low-resource Spoken Language Understanding","date":"2020-08-13","arxiv_id":"2008.05671","repositories_listed":0,"syntology":null},{"url":null,"slug":"lstm-acoustic-models-learn-to-align-and","title":"LSTM Acoustic Models Learn to Align and Pronounce with Graphemes","date":"2020-08-13","arxiv_id":"2008.06121","repositories_listed":0,"syntology":null},{"url":"/paper/masri-headset-a-maltese-corpus-for-speech-1","slug":"masri-headset-a-maltese-corpus-for-speech-1","title":"MASRI-HEADSET: A Maltese Corpus for Speech Recognition","date":"2020-08-13","arxiv_id":"2008.05760","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-using-eeg-signals-recorded","title":"Speech Recognition using EEG signals recorded using dry electrodes","date":"2020-08-13","arxiv_id":"2008.07621","repositories_listed":0,"syntology":null},{"url":null,"slug":"textual-echo-cancellation","title":"Textual Echo Cancellation","date":"2020-08-13","arxiv_id":"2008.06006","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-automatic-speech-recognition-with","title":"Online Automatic Speech Recognition with Listen, Attend and Spell Model","date":"2020-08-12","arxiv_id":"2008.05514","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-approaches-for-streaming","title":"Transfer Learning Approaches for Streaming End-to-End Speech Recognition System","date":"2020-08-12","arxiv_id":"2008.05086","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-with-bidirectional-decoder-for","title":"Transformer with Bidirectional Decoder for Speech Recognition","date":"2020-08-11","arxiv_id":"2008.04481","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-and-data-selection-for","title":"Knowledge Distillation and Data Selection for Semi-Supervised Learning in CTC Acoustic Models","date":"2020-08-10","arxiv_id":"2008.03923","repositories_listed":0,"syntology":null},{"url":null,"slug":"subword-regularization-an-analysis-of","title":"Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition","date":"2020-08-10","arxiv_id":"2008.04034","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinyspeech-attention-condensers-for-deep","title":"TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices","date":"2020-08-10","arxiv_id":"2008.04245","repositories_listed":0,"syntology":null},{"url":null,"slug":"lrspeech-extremely-low-resource-speech","title":"LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition","date":"2020-08-09","arxiv_id":"2008.03687","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-dereverberation-of","title":"Deep Learning Based Dereverberation of Temporal Envelopesfor Robust Speech Recognition","date":"2020-08-07","arxiv_id":"2008.03339","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-speaker-adaptation-methods","title":"Investigation of Speaker-adaptation methods in Transformer based ASR","date":"2020-08-07","arxiv_id":"2008.03247","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-transfer-learning-method-for-speech-emotion","title":"A Transfer Learning Method for Speech Emotion Recognition from Automatic Speech Recognition","date":"2020-08-06","arxiv_id":"2008.02863","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentive-fusion-enhanced-audio-visual","title":"Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition","date":"2020-08-06","arxiv_id":"2008.02686","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-transfer-learning-with-dynamic","title":"Federated Transfer Learning with Dynamic Gradient Aggregation","date":"2020-08-06","arxiv_id":"2008.02452","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-compression-of-end-to-end-asr-model","title":"Iterative Compression of End-to-End ASR Model using AutoML","date":"2020-08-06","arxiv_id":"2008.02897","repositories_listed":0,"syntology":null},{"url":null,"slug":"shouted-speech-compensation-for-speaker","title":"Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions","date":"2020-08-06","arxiv_id":"2008.02487","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-cross-domain-singing-voice","title":"Unsupervised Cross-Domain Singing Voice Conversion","date":"2020-08-06","arxiv_id":"2008.02830","repositories_listed":0,"syntology":null},{"url":"/paper/improving-end-to-end-speech-to-intent","slug":"improving-end-to-end-speech-to-intent","title":"Improving End-to-End Speech-to-Intent Classification with Reptile","date":"2020-08-05","arxiv_id":"2008.01994","repositories_listed":0,"syntology":null},{"url":null,"slug":"this-is-houston-say-again-please-the-behavox","title":"\"This is Houston. Say again, please\". The Behavox system for the Apollo-11 Fearless Steps Challenge (phase II)","date":"2020-08-04","arxiv_id":"2008.01504","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-construction-of-asr-systems","title":"Weakly Supervised Construction of ASR Systems with Massive Video Data","date":"2020-08-04","arxiv_id":"2008.01300","repositories_listed":0,"syntology":null},{"url":null,"slug":"tutornet-towards-flexible-knowledge","title":"TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition","date":"2020-08-03","arxiv_id":"2008.00671","repositories_listed":0,"syntology":null},{"url":null,"slug":"datamix-efficient-privacy-preserving-edge","title":"DataMix: Efficient Privacy-Preserving Edge-Cloud Inference","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-investigation-on-deep-learning-with-beta","title":"An Investigation on Deep Learning with Beta Stabilizer","date":"2020-07-31","arxiv_id":"2008.01173","repositories_listed":0,"syntology":null},{"url":null,"slug":"future-vector-enhanced-lstm-language-model","title":"Future Vector Enhanced LSTM Language Model for LVCSR","date":"2020-07-31","arxiv_id":"2008.01832","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-end-to-end-automatic-speech","title":"Modular End-to-end Automatic Speech Recognition Framework for Acoustic-to-word Model","date":"2020-07-31","arxiv_id":"2008.00953","repositories_listed":0,"syntology":null},{"url":null,"slug":"utterance-wise-meeting-transcription-system","title":"Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones","date":"2020-07-31","arxiv_id":"2007.15868","repositories_listed":0,"syntology":null},{"url":null,"slug":"developing-rnn-t-models-surpassing-high","title":"Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability","date":"2020-07-30","arxiv_id":"2007.15188","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-cross-lingual-knowledge-in","title":"Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource Languages","date":"2020-07-29","arxiv_id":"2007.15074","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-voice-analysis-via","title":"Privacy-preserving Voice Analysis via Disentangled Representations","date":"2020-07-29","arxiv_id":"2007.15064","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-kalman-filtering-for-speech","title":"Neural Kalman Filtering for Speech Enhancement","date":"2020-07-28","arxiv_id":"2007.13962","repositories_listed":0,"syntology":null},{"url":null,"slug":"team-deep-mixture-of-experts-for-distributed","title":"Team Deep Mixture of Experts for Distributed Power Control","date":"2020-07-28","arxiv_id":"2007.14147","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-minimum-word-error-rate-training-of","title":"Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition","date":"2020-07-27","arxiv_id":"2007.13802","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-super-resolution-based-on-deep-learning","title":"Video Super Resolution Based on Deep Learning: A Comprehensive Survey","date":"2020-07-25","arxiv_id":"2007.12928","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-gpgpu-to-recurrent-neural-network","title":"Applying GPGPU to Recurrent Neural Network Language Model based Fast Network Search in the Real-Time LVCSR","date":"2020-07-23","arxiv_id":"2007.11794","repositories_listed":0,"syntology":null},{"url":null,"slug":"effects-of-language-relatedness-for-cross-1","title":"Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models","date":"2020-07-22","arxiv_id":"2007.11648","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-adversarial-examples-for-robust-hybrid","title":"Audio Adversarial Examples for Robust Hybrid CTC/Attention Speech Recognition","date":"2020-07-21","arxiv_id":"2007.10723","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffrnn-differential-verification-of","title":"DiffRNN: Differential Verification of Recurrent Neural Networks","date":"2020-07-20","arxiv_id":"2007.10135","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-architecture-search-for-speech","title":"Neural Architecture Search For LF-MMI Trained Time Delay Neural Networks","date":"2020-07-17","arxiv_id":"2007.08818","repositories_listed":0,"syntology":null},{"url":null,"slug":"skipconvnet-skip-convolutional-neural-network","title":"SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation using Optimally Smoothed Spectral Mapping","date":"2020-07-17","arxiv_id":"2007.09131","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-an-automated-soap-note-classifying","title":"Towards an Automated SOAP Note: Classifying Utterances from Medical Conversations","date":"2020-07-17","arxiv_id":"2007.08749","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-analysis-of-polynomial-and","title":"Comparative Analysis of Polynomial and Rational Approximations of Hyperbolic Tangent Function for VLSI Implementation","date":"2020-07-13","arxiv_id":"2007.11976","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-implementation-of-hyperbolic-tangent","title":"Hardware Implementation of Hyperbolic Tangent Function using Catmull-Rom Spline Interpolation","date":"2020-07-13","arxiv_id":"2007.13516","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-faults-in-our-asrs-an-overview-of-attacks","title":"SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems","date":"2020-07-13","arxiv_id":"2007.06622","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-asru-2019-mandarin-english-code-switching","title":"The ASRU 2019 Mandarin-English Code-Switching Speech Recognition Challenge: Open Datasets, Tracks, Methods and Results","date":"2020-07-12","arxiv_id":"2007.05916","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-lm-and-word-mapping-for-contextual","title":"Class LM and word mapping for contextual biasing in End-to-End ASR","date":"2020-07-10","arxiv_id":"2007.05609","repositories_listed":0,"syntology":null}],"record_sha256":"a3ce86b143a2356781530b85dc1c91dd4eab67e9e96d0b439f1fdd128ffc16df","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}