{"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/25","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":25,"pages_in_order":31,"rows_per_page":100,"rows":[2401,2500],"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/24","next":"/task/automatic-speech-recognition/papers/26","papers":[{"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":"/paper/audio-visual-recognition-of-overlapped-speech","slug":"audio-visual-recognition-of-overlapped-speech","title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset","date":"2020-01-06","arxiv_id":"2001.01656","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},{"url":null,"slug":"191013215","title":"Transformer-based Cascaded Multimodal Speech Translation","date":"2019-10-29","arxiv_id":"1910.13215","repositories_listed":0,"syntology":null},{"url":null,"slug":"191013296","title":"Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation","date":"2019-10-29","arxiv_id":"1910.13296","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-speech-enhancement-of-publicly-available","title":"Does Speech enhancement of publicly available data help build robust Speech Recognition Systems?","date":"2019-10-29","arxiv_id":"1910.13488","repositories_listed":0,"syntology":null},{"url":null,"slug":"dfsmn-san-with-persistent-memory-model-for","title":"DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition","date":"2019-10-28","arxiv_id":"1910.13282","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-traing-for-sequence-to","title":"Unsupervised pre-training for sequence to sequence speech recognition","date":"2019-10-28","arxiv_id":"1910.12418","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-for-end-to-end-low-resource","title":"Meta Learning for End-to-End Low-Resource Speech Recognition","date":"2019-10-26","arxiv_id":"1910.12094","repositories_listed":0,"syntology":null},{"url":null,"slug":"l2rs-a-learning-to-rescore-mechanism-for","title":"L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11496","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-online-end-to-end-transformer","title":"Towards Online End-to-end Transformer Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11871","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-in-deep-reinforcement-learning","title":"Pre-training in Deep Reinforcement Learning for Automatic Speech Recognition","date":"2019-10-24","arxiv_id":"1910.11256","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-long-form-speech-using-streaming","title":"Recognizing long-form speech using streaming end-to-end models","date":"2019-10-24","arxiv_id":"1910.11455","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-practical-two-stage-training-strategy-for","title":"A practical two-stage training strategy for multi-stream end-to-end speech recognition","date":"2019-10-23","arxiv_id":"1910.10671","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-asr-pretraining-for-low-resource","title":"Analyzing ASR pretraining for low-resource speech-to-text translation","date":"2019-10-23","arxiv_id":"1910.10762","repositories_listed":0,"syntology":null},{"url":null,"slug":"correction-of-automatic-speech-recognition","title":"Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model","date":"2019-10-23","arxiv_id":"1910.10697","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-online-spoken-language","title":"RNN based Incremental Online Spoken Language Understanding","date":"2019-10-23","arxiv_id":"1910.10287","repositories_listed":0,"syntology":null},{"url":null,"slug":"g2g-tts-driven-pronunciation-learning-for","title":"G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR","date":"2019-10-22","arxiv_id":"1910.12612","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-neural-machine-translation-for-clean","title":"Robust Neural Machine Translation for Clean and Noisy Speech Transcripts","date":"2019-10-22","arxiv_id":"1910.10238","repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptual-speech-enhancement-via-generative","title":"AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks","date":"2019-10-21","arxiv_id":"1910.12620","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-serket-development-of-integrative","title":"Neuro-SERKET: Development of Integrative Cognitive System through the Composition of Deep Probabilistic Generative Models","date":"2019-10-20","arxiv_id":"1910.08918","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-talker-mvdr-beamforming-based-on","title":"Multi-Talker MVDR Beamforming Based on Extended Complex Gaussian Mixture Model","date":"2019-10-17","arxiv_id":"1910.07753","repositories_listed":0,"syntology":null},{"url":null,"slug":"lead2gold-towards-exploiting-the-full","title":"Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition","date":"2019-10-16","arxiv_id":"1910.07323","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-asr-with-contextual-block","title":"Transformer ASR with Contextual Block Processing","date":"2019-10-16","arxiv_id":"1910.07204","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-large-receptive-field-convolutional","title":"Analyzing Large Receptive Field Convolutional Networks for Distant Speech Recognition","date":"2019-10-15","arxiv_id":"1910.07047","repositories_listed":0,"syntology":null},{"url":null,"slug":"vais-asr-building-a-conversational-speech","title":"VAIS ASR: Building a conversational speech recognition system using language model combination","date":"2019-10-12","arxiv_id":"1910.05603","repositories_listed":0,"syntology":null},{"url":null,"slug":"hear-no-evil-see-kenansville-efficient-and","title":"Hear \"No Evil\", See \"Kenansville\": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systems","date":"2019-10-11","arxiv_id":"1910.05262","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-by-example-on-device-keyword-spotting","title":"Query-by-example on-device keyword spotting","date":"2019-10-11","arxiv_id":"1910.05171","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-to-many-multilingual-end-to-end-speech","title":"One-To-Many Multilingual End-to-end Speech Translation","date":"2019-10-08","arxiv_id":"1910.03320","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-case-study-on-combining-asr-and-visual","title":"A Case Study on Combining ASR and Visual Features for Generating Instructional Video Captions","date":"2019-10-07","arxiv_id":"1910.02930","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-a-framenet-semantic-parser-for","title":"Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning","date":"2019-10-07","arxiv_id":"1910.02734","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-confidence-in-sequence-to-sequence","title":"Modeling Confidence in Sequence-to-Sequence Models","date":"2019-10-04","arxiv_id":"1910.01859","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-zero-inflated-quality-estimation-model","title":"Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System","date":"2019-10-03","arxiv_id":"1910.01289","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-senones-to-chenones-tied-context","title":"From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition","date":"2019-10-02","arxiv_id":"1910.01493","repositories_listed":0,"syntology":null},{"url":null,"slug":"shi-yong-sheng-cheng-dui-kang-wang-lu-yu","title":"使用生成對抗網路於強健式自動語音辨識的應用(Exploiting Generative Adversarial Network for Robustness Automatic Speech Recognition)","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-code-switching-asr-for-low","title":"End-to-End Code-Switching ASR for Low-Resourced Language Pairs","date":"2019-09-27","arxiv_id":"1909.12681","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-data-barrier-towards-robust","title":"Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training","date":"2019-09-25","arxiv_id":"1909.11430","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-robust-audio-adversarial-examples","title":"Generating Robust Audio Adversarial Examples using Iterative Proportional Clipping","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-training-techniques-for-online","title":"Improved Training Techniques for Online Neural Machine Translation","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","repositories_listed":0,"syntology":null},{"url":null,"slug":"190909993","title":"Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR","date":"2019-09-22","arxiv_id":"1909.09993","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switched-language-models-using-neural","title":"Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences","date":"2019-09-18","arxiv_id":"1909.08582","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-speech-recognition-and-speaker","title":"Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models","date":"2019-09-17","arxiv_id":"1909.08103","repositories_listed":0,"syntology":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":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":"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}],"record_sha256":"d9fcee617adb179aa8e3e1212d657b7aac530e7045f77ce4e1625130cb27fbae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}