{"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/27","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":27,"pages_in_order":32,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/task/automatic-speech-recognition-2/papers/28","papers":[{"url":null,"slug":"fully-convolutional-asr-for-less-resourced","title":"Fully Convolutional ASR for Less-Resourced Endangered Languages","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-language-model-for-low-resource","title":"Improving the Language Model for Low-Resource ASR with Online Text Corpora","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-corpus-of-czech-parliament-plenary","title":"Large Corpus of Czech Parliament Plenary Hearings","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-vocabulary-read-speech-corpora-for-four","title":"Large Vocabulary Read Speech Corpora for Four Ethiopian Languages: Amharic, Tigrigna, Oromo and Wolaytta","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linto-platform-a-smart-open-voice-assistant","title":"LinTO Platform: A Smart Open Voice Assistant for Business Environments","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"malayalam-speech-corpus-design-and","title":"Malayalam Speech Corpus: Design and Development for Dravidian Language","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-staged-cross-lingual-acoustic-model","title":"Multi-Staged Cross-Lingual Acoustic Model Adaption for Robust Speech Recognition in Real-World Applications - A Case Study on German Oral History Interviews","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-construction-of-the-asr-oriented-indian","title":"On Construction of the ASR-oriented Indian English Pronunciation Dictionary","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/open-source-high-quality-speech-datasets-for","slug":"open-source-high-quality-speech-datasets-for","title":"Open-Source High Quality Speech Datasets for Basque, Catalan and Galician","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-corpus-for-japanese-spoken-to","title":"Parallel Corpus for Japanese Spoken-to-Written Style Conversion","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phonemic-transcription-of-low-resource","title":"Phonemic Transcription of Low-Resource Languages: To What Extent can Preprocessing be Automated?","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"preparation-of-bangla-speech-corpus-from","title":"Preparation of Bangla Speech Corpus from Publicly Available Audio \\& Text","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rsc-a-romanian-read-speech-corpus-for","title":"RSC: A Romanian Read Speech Corpus for Automatic Speech Recognition","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"samr-omur-crowd-sourcing-data-collection-for","title":"Samr\\'omur: Crowd-sourcing Data Collection for Icelandic Speech Recognition","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-safe-t-corpus-a-new-resource-for","title":"The SAFE-T Corpus: A New Resource for Simulated Public Safety Communications","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-building-an-automatic-transcription","title":"Towards Building an Automatic Transcription System for Language Documentation: Experiences from Muyu","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-less-resourced-semitic","title":"Transfer Learning for Less-Resourced Semitic Languages Speech Recognition: the Case of Amharic","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-automatic-speech-recognition-in-spoken","title":"Using Automatic Speech Recognition in Spoken Corpus Curation","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"where-are-we-in-named-entity-recognition-from","title":"Where are we in Named Entity Recognition from Speech?","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multiresolution-and-multimodal-speech","title":"Multiresolution and Multimodal Speech Recognition with Transformers","date":"2020-04-29","arxiv_id":"2004.14840","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-trained-transformers-models-for","title":"Jointly Trained Transformers models for Spoken Language Translation","date":"2020-04-25","arxiv_id":"2004.12111","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-to-dialog-act-recognition","title":"End-to-end speech-to-dialog-act recognition","date":"2020-04-23","arxiv_id":"2004.11419","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-non-autoregressive-model-for","title":"A Study of Non-autoregressive Model for Sequence Generation","date":"2020-04-22","arxiv_id":"2004.10454","repositories_listed":0,"syntology":null},{"url":null,"slug":"punctuation-prediction-in-spontaneous","title":"Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?","date":"2020-04-13","arxiv_id":"2004.05985","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-diarization-with-lexical-information-1","title":"Speaker Diarization with Lexical Information","date":"2020-04-13","arxiv_id":"2004.06756","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-readability-for-automatic-speech","title":"Improving Readability for Automatic Speech Recognition Transcription","date":"2020-04-09","arxiv_id":"2004.04438","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-modelling-for-five","title":"Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech","date":"2020-04-08","arxiv_id":"2004.06480","repositories_listed":0,"syntology":null},{"url":null,"slug":"homophone-based-label-smoothing-in-end-to-end","title":"Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition","date":"2020-04-07","arxiv_id":"2004.03437","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-speech-adversarial-examples","title":"Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement","date":"2020-03-31","arxiv_id":"2003.13917","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-latency-asr-for-simultaneous-speech","title":"Low Latency ASR for Simultaneous Speech Translation","date":"2020-03-22","arxiv_id":"2003.09891","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-for-speech-recognition-on","title":"Training for Speech Recognition on Coprocessors","date":"2020-03-22","arxiv_id":"2003.12366","repositories_listed":0,"syntology":null},{"url":null,"slug":"deliberation-model-based-two-pass-end-to-end","title":"Deliberation Model Based Two-Pass End-to-End Speech Recognition","date":"2020-03-17","arxiv_id":"2003.07962","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-accuracy-and-low-latency-speech","title":"High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model","date":"2020-03-17","arxiv_id":"2003.07482","repositories_listed":0,"syntology":null},{"url":null,"slug":"asr-error-correction-and-domain-adaptation","title":"ASR Error Correction and Domain Adaptation Using Machine Translation","date":"2020-03-13","arxiv_id":"2003.07692","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-autoregressive-transducer-hat","title":"Hybrid Autoregressive Transducer (hat)","date":"2020-03-12","arxiv_id":"2003.07705","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-networks-for-automatic-speech","title":"Deep Neural Networks for Automatic Speech Processing: A Survey from Large Corpora to Limited Data","date":"2020-03-09","arxiv_id":"2003.04241","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-noise-robust-automatic-speech","title":"Improving noise robust automatic speech recognition with single-channel time-domain enhancement network","date":"2020-03-09","arxiv_id":"2003.03998","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-time-delay-transformer-for-real","title":"Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection","date":"2020-03-03","arxiv_id":"2003.01309","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-uyghur-asr-systems-with-decoders","title":"Improving Uyghur ASR systems with decoders using morpheme-based language models","date":"2020-03-03","arxiv_id":"2003.01509","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-density-ratio-approach-to-language-model","title":"A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition","date":"2020-02-26","arxiv_id":"2002.11268","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-training-of-deep-neural-network","title":"Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition","date":"2020-02-24","arxiv_id":"2002.10502","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-asr-with-lightweight-and","title":"Attention-based ASR with Lightweight and Dynamic Convolutions","date":"2020-02-20","arxiv_id":"1912.11793","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-adjusted-neuron-activation-profiles","title":"Gradient-Adjusted Neuron Activation Profiles for Comprehensive Introspection of Convolutional Speech Recognition Models","date":"2020-02-19","arxiv_id":"2002.08125","repositories_listed":0,"syntology":null},{"url":null,"slug":"rtmobile-beyond-real-time-mobile-acceleration","title":"RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition","date":"2020-02-19","arxiv_id":"2002.11474","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-corpus-of-ainu-folklore-and-end-to-end","title":"Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language","date":"2020-02-16","arxiv_id":"2002.06675","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speaker-adaptation-using","title":"Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR","date":"2020-02-14","arxiv_id":"2002.06165","repositories_listed":0,"syntology":null},{"url":null,"slug":"looking-enhances-listening-recovering-missing","title":"Looking Enhances Listening: Recovering Missing Speech Using Images","date":"2020-02-13","arxiv_id":"2002.05639","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-diverse-and-natural-text-to-speech","title":"Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior","date":"2020-02-06","arxiv_id":"2002.03788","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-multi-channel-speech-recognition-using","title":"Robust Multi-channel Speech Recognition using Frequency Aligned Network","date":"2020-02-06","arxiv_id":"2002.02520","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-mind-reading","title":"Continuous Silent Speech Recognition using EEG","date":"2020-02-06","arxiv_id":"2002.03851","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-automatic-speech-recognition","title":"End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection","date":"2020-02-03","arxiv_id":"2002.00551","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogue-based-simulation-for-cultural","title":"Dialogue-Based Simulation For Cultural Awareness Training","date":"2020-02-01","arxiv_id":"2002.00223","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-learnable-front-end-for-multi-channel","title":"Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning","date":"2020-02-01","arxiv_id":"2002.00125","repositories_listed":0,"syntology":null},{"url":null,"slug":"but-opensat-2019-speech-recognition-system","title":"BUT Opensat 2019 Speech Recognition System","date":"2020-01-30","arxiv_id":"2001.11360","repositories_listed":0,"syntology":null},{"url":null,"slug":"environment-aware-reconfigurable-noise","title":"Environment-aware Reconfigurable Noise Suppression","date":"2020-01-29","arxiv_id":"2001.10718","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-contextual-modeling-for-asr-correction","title":"Joint Contextual Modeling for ASR Correction and Language Understanding","date":"2020-01-28","arxiv_id":"2002.00750","repositories_listed":0,"syntology":null},{"url":null,"slug":"lattice-based-improvements-for-voice","title":"Lattice-based Improvements for Voice Triggering Using Graph Neural Networks","date":"2020-01-25","arxiv_id":"2001.10822","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-gradient-approximation-for-memory","title":"Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Network","date":"2020-01-24","arxiv_id":"2001.08885","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-asr-by-end-to-end-self","title":"Semi-supervised ASR by End-to-end Self-training","date":"2020-01-24","arxiv_id":"2001.09128","repositories_listed":0,"syntology":null},{"url":null,"slug":"tlt-school-a-corpus-of-non-native-children","title":"TLT-school: a Corpus of Non Native Children Speech","date":"2020-01-22","arxiv_id":"2001.08051","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-online-ctcattention-end-to","title":"Transformer-based Online CTC/attention End-to-End Speech Recognition Architecture","date":"2020-01-15","arxiv_id":"2001.08290","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-spoken-language-understanding-by","title":"Improving Spoken Language Understanding By Exploiting ASR N-best Hypotheses","date":"2020-01-11","arxiv_id":"2001.05284","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-dysarthric-speech-intelligibility","title":"Improving Dysarthric Speech Intelligibility Using Cycle-consistent Adversarial Training","date":"2020-01-10","arxiv_id":"2001.04260","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-challenge-for-correcting-errors-of","title":"Open Challenge for Correcting Errors of Speech Recognition Systems","date":"2020-01-09","arxiv_id":"2001.03041","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-automatic-speech-recognition-with","title":"Streaming automatic speech recognition with the transformer model","date":"2020-01-08","arxiv_id":"2001.02674","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-and-analysis-of-hyper-and-hypo","title":"Investigation and Analysis of Hyper and Hypo neuron pruning to selectively update neurons during Unsupervised Adaptation","date":"2020-01-06","arxiv_id":"2001.01755","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-on-device-streaming-speech","title":"Attention based on-device streaming speech recognition with large speech corpus","date":"2020-01-02","arxiv_id":"2001.00577","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-representation-learning-in-speech","title":"Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends","date":"2020-01-02","arxiv_id":"2001.00378","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-aware-speech-transformer","title":"Speaker-aware speech-transformer","date":"2020-01-02","arxiv_id":"2001.01557","repositories_listed":0,"syntology":null},{"url":null,"slug":"eeg-based-continuous-speech-recognition-using","title":"EEG based Continuous Speech Recognition using Transformers","date":"2019-12-31","arxiv_id":"2001.00501","repositories_listed":0,"syntology":null},{"url":null,"slug":"power-law-nonlinearity-with-maximally-uniform","title":"power-law nonlinearity with maximally uniform distribution criterion for improved neural network training in automatic speech recognition","date":"2019-12-22","arxiv_id":"1912.11041","repositories_listed":0,"syntology":null},{"url":null,"slug":"role-of-non-linear-data-processing-on-speech","title":"Role of non-linear data processing on speech recognition task in the framework of reservoir computing","date":"2019-12-19","arxiv_id":"1906.02812","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-testing-on-asr-performance-via","title":"Statistical Testing on ASR Performance via Blockwise Bootstrap","date":"2019-12-19","arxiv_id":"1912.09508","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cycle-gan-approach-to-model-natural","title":"A Cycle-GAN Approach to Model Natural Perturbations in Speech for ASR Applications","date":"2019-12-18","arxiv_id":"1912.11151","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-speech-recognition-using-eeg-and","title":"Continuous Speech Recognition using EEG and Video","date":"2019-12-16","arxiv_id":"1912.07730","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-neural-phone-recognition-of-mixed-source","title":"On Neural Phone Recognition of Mixed-Source ECoG Signals","date":"2019-12-12","arxiv_id":"1912.05869","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-end-to-end-speech-recognition-with","title":"Leveraging End-to-End Speech Recognition with Neural Architecture Search","date":"2019-12-11","arxiv_id":"1912.05946","repositories_listed":0,"syntology":null},{"url":null,"slug":"specaugment-on-large-scale-datasets","title":"SpecAugment on Large Scale Datasets","date":"2019-12-11","arxiv_id":"1912.05533","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-attention-discriminative-language-model","title":"Audio-attention discriminative language model for ASR rescoring","date":"2019-12-06","arxiv_id":"1912.03363","repositories_listed":0,"syntology":null},{"url":"/paper/asr-is-all-you-need-cross-modal-distillation","slug":"asr-is-all-you-need-cross-modal-distillation","title":"ASR is all you need: cross-modal distillation for lip reading","date":"2019-11-28","arxiv_id":"1911.12747","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-the-next-generation-of-intelligent","title":"Designing the Next Generation of Intelligent Personal Robotic Assistants for the Physically Impaired","date":"2019-11-28","arxiv_id":"1911.12482","repositories_listed":0,"syntology":null},{"url":null,"slug":"atcspeech-a-multilingual-pilot-controller","title":"ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment","date":"2019-11-26","arxiv_id":"1911.11365","repositories_listed":0,"syntology":null},{"url":null,"slug":"independent-language-modeling-architecture","title":"Independent language modeling architecture for end-to-end ASR","date":"2019-11-25","arxiv_id":"1912.00863","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-eeg-based-continuous-speech","title":"Improving EEG based Continuous Speech Recognition","date":"2019-11-24","arxiv_id":"1911.11610","repositories_listed":0,"syntology":null},{"url":null,"slug":"cantonese-automatic-speech-recognition-using","title":"Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin","date":"2019-11-21","arxiv_id":"1911.09271","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-using-2d-sequence-to-sequence-models-for","title":"On using 2D sequence-to-sequence models for speech recognition","date":"2019-11-20","arxiv_id":"1911.08888","repositories_listed":0,"syntology":null},{"url":null,"slug":"3-d-feature-and-acoustic-modeling-for-far","title":"3-D Feature and Acoustic Modeling for Far-Field Speech Recognition","date":"2019-11-13","arxiv_id":"1911.05504","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-adversarial-representation","title":"Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?","date":"2019-11-12","arxiv_id":"1911.04913","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-direct-speech-to-text","title":"Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning","date":"2019-11-11","arxiv_id":"1911.04283","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-voice-conversion-based-privacy","title":"Evaluating Voice Conversion-based Privacy Protection against Informed Attackers","date":"2019-11-10","arxiv_id":"1911.03934","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-autoregressive-transformer-automatic","title":"Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition","date":"2019-11-10","arxiv_id":"1911.04908","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-adaptation-for-attention-based-end-to","title":"Speaker Adaptation for Attention-Based End-to-End Speech Recognition","date":"2019-11-09","arxiv_id":"1911.03762","repositories_listed":0,"syntology":null},{"url":"/paper/europarl-st-a-multilingual-corpus-for-speech","slug":"europarl-st-a-multilingual-corpus-for-speech","title":"Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates","date":"2019-11-08","arxiv_id":"1911.03167","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-error-simulation-techniques","title":"Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery","date":"2019-11-08","arxiv_id":"1911.03378","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-end-to-end-models-for-long","title":"A comparison of end-to-end models for long-form speech recognition","date":"2019-11-06","arxiv_id":"1911.02242","repositories_listed":0,"syntology":null},{"url":null,"slug":"rnn-t-for-latency-controlled-asr-with","title":"RNN-T For Latency Controlled ASR With Improved Beam Search","date":"2019-11-05","arxiv_id":"1911.01629","repositories_listed":0,"syntology":null},{"url":null,"slug":"lstm-sharp-an-adaptable-energy-efficient","title":"SHARP: An Adaptable, Energy-Efficient Accelerator for Recurrent Neural Network","date":"2019-11-04","arxiv_id":"1911.01258","repositories_listed":0,"syntology":null},{"url":null,"slug":"chameleon-a-language-model-adaptation-toolkit","title":"Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-augmentation-for-end-to-end-speech","title":"Data Augmentation for End-to-End Speech Translation: FBK@IWSLT ‘19","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"entity-resolution-for-noisy-asr-transcripts","title":"Entity resolution for noisy ASR transcripts","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"4a2d97538824f814fd423389a450a93e66ca371e0dcb031f675cc41741af4006","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}