{"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/30","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":30,"pages_in_order":32,"rows_per_page":100,"rows":[2901,3000],"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/29","next":"/task/automatic-speech-recognition-2/papers/31","papers":[{"url":null,"slug":"the-afrl-iwslt-2018-systems-what-worked-what","title":"The AFRL IWSLT 2018 Systems: What Worked, What Didn’t","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-sogou-tiic-speech-translation-system-for","title":"The Sogou-TIIC Speech Translation System for IWSLT 2018","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-spoken-word-posterior-features-in","title":"Using Spoken Word Posterior Features in Neural Machine Translation","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-audio-adversarial-examples","title":"Characterizing Audio Adversarial Examples Using Temporal Dependency","date":"2018-09-28","arxiv_id":"1809.10875","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-multi-lingual-multi-speaker-speech","title":"End-to-End Multi-Lingual Multi-Speaker Speech Recognition","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-audio-to-semantics-approaches-to-end-to","title":"From Audio to Semantics: Approaches to end-to-end spoken language understanding","date":"2018-09-24","arxiv_id":"1809.09190","repositories_listed":0,"syntology":null},{"url":null,"slug":"hindi-english-code-switching-speech-corpus","title":"Hindi-English Code-Switching Speech Corpus","date":"2018-09-24","arxiv_id":"1810.00662","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-audiovisual-speech-activity","title":"End-to-end Audiovisual Speech Activity Detection with Bimodal Recurrent Neural Models","date":"2018-09-12","arxiv_id":"1809.04553","repositories_listed":0,"syntology":null},{"url":null,"slug":"isolated-and-ensemble-audio-preprocessing","title":"Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognition","date":"2018-09-11","arxiv_id":"1809.04397","repositories_listed":0,"syntology":null},{"url":null,"slug":"etude-de-linformativite-des-transcriptions","title":"Étude de l'informativité des transcriptions : une approche basée sur le résumé automatique","date":"2018-09-04","arxiv_id":"1809.00994","repositories_listed":0,"syntology":null},{"url":null,"slug":"hasp-a-high-performance-adaptive-mobile","title":"HASP: A High-Performance Adaptive Mobile Security Enhancement Against Malicious Speech Recognition","date":"2018-09-04","arxiv_id":"1809.01697","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenting-bottleneck-features-of-deep-neural","title":"Augmenting Bottleneck Features of Deep Neural Network Employing Motor State for Speech Recognition at Humanoid Robots","date":"2018-08-27","arxiv_id":"1808.08702","repositories_listed":0,"syntology":null},{"url":null,"slug":"role-of-intonation-in-scoring-spoken-english","title":"Role of Intonation in Scoring Spoken English","date":"2018-08-23","arxiv_id":"1808.07688","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-domain-invariant-speech-recognition","title":"Toward domain-invariant speech recognition via large scale training","date":"2018-08-16","arxiv_id":"1808.05312","repositories_listed":0,"syntology":null},{"url":null,"slug":"densely-connected-convolutional-networks-for","title":"Densely Connected Convolutional Networks for Speech Recognition","date":"2018-08-10","arxiv_id":"1808.03570","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-recognition-with-word-based","title":"End-to-end Speech Recognition with Word-based RNN Language Models","date":"2018-08-08","arxiv_id":"1808.02608","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-context-end-to-end-contextual-speech","title":"Deep context: end-to-end contextual speech recognition","date":"2018-08-07","arxiv_id":"1808.02480","repositories_listed":0,"syntology":null},{"url":null,"slug":"device-directed-utterance-detection","title":"Device-directed Utterance Detection","date":"2018-08-07","arxiv_id":"1808.02504","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-and-textual-data-augmentation-for","title":"Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech","date":"2018-07-28","arxiv_id":"1807.10945","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulatory-features-for-asr-of-pathological","title":"Articulatory Features for ASR of Pathological Speech","date":"2018-07-28","arxiv_id":"1807.10948","repositories_listed":0,"syntology":null},{"url":null,"slug":"back-translation-style-data-augmentation-for","title":"Back-Translation-Style Data Augmentation for End-to-End ASR","date":"2018-07-28","arxiv_id":"1807.10893","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-a-unified-code-switching-asr-system","title":"Building a Unified Code-Switching ASR System for South African Languages","date":"2018-07-28","arxiv_id":"1807.10949","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-switching-detection-with-data-augmented","title":"Code-Switching Detection with Data-Augmented Acoustic and Language Models","date":"2018-07-28","arxiv_id":"1808.00521","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-for-humanitarian","title":"Automatic Speech Recognition for Humanitarian Applications in Somali","date":"2018-07-23","arxiv_id":"1807.08669","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-multi-task-learning-with-ctc","title":"Hierarchical Multi Task Learning With CTC","date":"2018-07-18","arxiv_id":"1807.07104","repositories_listed":0,"syntology":null},{"url":null,"slug":"concept-based-embeddings-for-natural-language","title":"Concept-Based Embeddings for Natural Language Processing","date":"2018-07-15","arxiv_id":"1807.05519","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-ctc-attention-based-end-to-end-speech","title":"Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units","date":"2018-07-13","arxiv_id":"1807.04978","repositories_listed":0,"syntology":null},{"url":null,"slug":"foreign-english-accent-adjustment-by-learning","title":"Foreign English Accent Adjustment by Learning Phonetic Patterns","date":"2018-07-09","arxiv_id":"1807.03625","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-neural-architecture-for-joint","title":"A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-machine-transliteration-using","title":"Low-Resource Machine Transliteration Using Recurrent Neural Networks of Asian Languages","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"openseq2seq-extensible-toolkit-for","title":"OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phone-merging-for-code-switched-speech","title":"Phone Merging For Code-Switched Speech Recognition","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-and-efficient-vocabulary","title":"Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR","date":"2018-06-27","arxiv_id":"1806.10306","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-language-model-adaptation-for","title":"Contextual Language Model Adaptation for Conversational Agents","date":"2018-06-26","arxiv_id":"1806.10215","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automated-single-channel-source","title":"Towards Automated Single Channel Source Separation using Neural Networks","date":"2018-06-21","arxiv_id":"1806.08086","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-adapted-beamforming-for-multi-channel","title":"Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition","date":"2018-06-19","arxiv_id":"1806.07407","repositories_listed":0,"syntology":null},{"url":null,"slug":"extending-recurrent-neural-aligner-for","title":"Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin","date":"2018-06-17","arxiv_id":"1806.06342","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-adaptation-with-interpretable","title":"Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognition","date":"2018-06-13","arxiv_id":"1806.04872","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-end-to-end-speech-recognition","title":"Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages","date":"2018-06-12","arxiv_id":"1806.05059","repositories_listed":0,"syntology":null},{"url":null,"slug":"binarized-lstm-language-model","title":"Binarized LSTM Language Model","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"role-specific-language-models-for-processing","title":"Role-specific Language Models for Processing Recorded Neuropsychological Exams","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adagio-interactive-experimentation-with","title":"ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio","date":"2018-05-30","arxiv_id":"1805.11852","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-named-entity-extraction-from","title":"End-to-end named entity extraction from speech","date":"2018-05-30","arxiv_id":"1805.12045","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-speaker-segmentation-and","title":"Multimodal Speaker Segmentation and Diarization using Lexical and Acoustic Cues via Sequence to Sequence Neural Networks","date":"2018-05-28","arxiv_id":"1805.10731","repositories_listed":0,"syntology":null},{"url":null,"slug":"asr-based-features-for-emotion-recognition-a","title":"ASR-based Features for Emotion Recognition: A Transfer Learning Approach","date":"2018-05-23","arxiv_id":"1805.09197","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-cross-modal-alignment-of-speech","title":"Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces","date":"2018-05-18","arxiv_id":"1805.07467","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-modeling-units-in-sequence-to","title":"A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese","date":"2018-05-16","arxiv_id":"1805.06239","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-asr-for-under-resourced-languages","title":"Improved ASR for Under-Resourced Languages Through Multi-Task Learning with Acoustic Landmarks","date":"2018-05-15","arxiv_id":"1805.05574","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-from-adult-to-children-for","title":"Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations","date":"2018-05-08","arxiv_id":"1805.03322","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-noise-robustness-of-acoustic-model","title":"Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training","date":"2018-05-02","arxiv_id":"1805.01357","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-pronunciation-modeling-of-swiss","title":"Data-Driven Pronunciation Modeling of Swiss German Dialectal Speech for Automatic Speech Recognition","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-corpora-in-mboshi-bantu-c25-congo","title":"Parallel Corpora in Mboshi (Bantu C25, Congo-Brazzaville)","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phonetically-balanced-code-mixed-speech","title":"Phonetically Balanced Code-Mixed Speech Corpus for Hindi-English Automatic Speech Recognition","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-documentation-of-icd-codes-with-far","title":"Automatic Documentation of ICD Codes with Far-Field Speech Recognition","date":"2018-04-30","arxiv_id":"1804.11046","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-multimodal-speech-recognition","title":"End-to-End Multimodal Speech Recognition","date":"2018-04-25","arxiv_id":"1804.09713","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-for-launch","title":"Automatic speech recognition for launch control center communication using recurrent neural networks with data augmentation and custom language model","date":"2018-04-24","arxiv_id":"1804.09552","repositories_listed":0,"syntology":null},{"url":null,"slug":"precise-detection-of-speech-endpoints","title":"Precise Detection of Speech Endpoints Dynamically: A Wavelet Convolution based approach","date":"2018-04-17","arxiv_id":"1804.06159","repositories_listed":0,"syntology":null},{"url":"/paper/neural-network-language-modeling-with-letter","slug":"neural-network-language-modeling-with-letter","title":"Neural Network Language Modeling with Letter-based Features and Importance Sampling","date":"2018-04-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-recognition-using-time-delay-deep","title":"Language Recognition using Time Delay Deep Neural Network","date":"2018-04-13","arxiv_id":"1804.05000","repositories_listed":0,"syntology":null},{"url":null,"slug":"espnet-end-to-end-speech-processing-toolkit","title":"ESPnet: End-to-End Speech Processing Toolkit","date":"2018-03-30","arxiv_id":"1804.00015","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unsupervised-automatic-speech","title":"Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only","date":"2018-03-29","arxiv_id":"1803.10952","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-speech-chain-with-one-shot-speaker","title":"Machine Speech Chain with One-shot Speaker Adaptation","date":"2018-03-28","arxiv_id":"1803.10525","repositories_listed":0,"syntology":null},{"url":"/paper/the-fifth-chime-speech-separation-and","slug":"the-fifth-chime-speech-separation-and","title":"The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines","date":"2018-03-28","arxiv_id":"1803.10609","repositories_listed":0,"syntology":null},{"url":"/paper/building-state-of-the-art-distant-speech","slug":"building-state-of-the-art-distant-speech","title":"Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline","date":"2018-03-27","arxiv_id":"1803.10109","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-data-augmentation-for-end-to-end","title":"Multi-Modal Data Augmentation for End-to-End ASR","date":"2018-03-27","arxiv_id":"1803.10299","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-aware-design-of-a-deep-convolutional","title":"Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion","date":"2018-03-13","arxiv_id":"1803.04840","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-domain-invariant-features-by","title":"Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition","date":"2018-03-07","arxiv_id":"1803.02551","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-modular-training-of-neural-acoustics-to","title":"On Modular Training of Neural Acoustics-to-Word Model for LVCSR","date":"2018-03-03","arxiv_id":"1803.01090","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-automatic-speech-recognition-in","title":"Evaluating Automatic Speech Recognition in Translation","date":"2018-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-derivational-entropy-of-left-to-right","title":"On the Derivational Entropy of Left-to-Right Probabilistic Finite-State Automata and Hidden Markov Models","date":"2018-03-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-and-topic","title":"Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages","date":"2018-02-23","arxiv_id":"1802.08731","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-modeling-of-accents-and-acoustics-for","title":"Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition","date":"2018-02-07","arxiv_id":"1802.02656","repositories_listed":0,"syntology":null},{"url":null,"slug":"phonetic-and-graphemic-systems-for-multi","title":"Phonetic and Graphemic Systems for Multi-Genre Broadcast Transcription","date":"2018-02-01","arxiv_id":"1802.00254","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-corpus-for-modeling-word-importance-in","title":"A Corpus for Modeling Word Importance in Spoken Dialogue Transcripts","date":"2018-01-29","arxiv_id":"1801.09746","repositories_listed":0,"syntology":null},{"url":null,"slug":"commandersong-a-systematic-approach-for","title":"CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition","date":"2018-01-24","arxiv_id":"1801.08535","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-training-and-cross-lingual","title":"Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model","date":"2018-01-23","arxiv_id":"1711.10025","repositories_listed":0,"syntology":null},{"url":null,"slug":"new-baseline-in-automatic-speech-recognition","title":"New Baseline in Automatic Speech Recognition for Northern S\\'ami","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-dialog-policies-in-noisy","title":"Learning Robust Dialog Policies in Noisy Environments","date":"2017-12-11","arxiv_id":"1712.04034","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-competitive-direct-acoustics-to-word","title":"Building competitive direct acoustics-to-word models for English conversational speech recognition","date":"2017-12-08","arxiv_id":"1712.03133","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-incorporating-an-external","title":"An analysis of incorporating an external language model into a sequence-to-sequence model","date":"2017-12-06","arxiv_id":"1712.01996","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-nontrivial-connectivity-for","title":"Exploiting Nontrivial Connectivity for Automatic Speech Recognition","date":"2017-11-28","arxiv_id":"1711.10271","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-adaptation-with-domain","title":"Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition","date":"2017-11-21","arxiv_id":"1711.08010","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-pur-an-energy-efficient-processing-unit-for","title":"E-PUR: An Energy-Efficient Processing Unit for Recurrent Neural Networks","date":"2017-11-20","arxiv_id":"1711.07480","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-for-medical-conversations","title":"Speech recognition for medical conversations","date":"2017-11-20","arxiv_id":"1711.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-speech-enhancement-with-generative","title":"Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition","date":"2017-11-15","arxiv_id":"1711.05747","repositories_listed":0,"syntology":null},{"url":null,"slug":"phonemic-and-graphemic-multilingual-ctc-based","title":"Phonemic and Graphemic Multilingual CTC Based Speech Recognition","date":"2017-11-13","arxiv_id":"1711.04564","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-speech-recognition-with-a-single","title":"Multilingual Speech Recognition With A Single End-To-End Model","date":"2017-11-06","arxiv_id":"1711.01694","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-language-models-for-code-switched-speech","title":"Dual Language Models for Code Switched Speech Recognition","date":"2017-11-03","arxiv_id":"1711.01048","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-black-box-speech-recognition-using","title":"Improving Black-box Speech Recognition using Semantic Parsing","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-asr-optimization-via","title":"Sequence-to-Sequence ASR Optimization via Reinforcement Learning","date":"2017-10-30","arxiv_id":"1710.10774","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-all-convolutional-encoders-for","title":"A Study of All-Convolutional Encoders for Connectionist Temporal Classification","date":"2017-10-28","arxiv_id":"1710.10398","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridgenets-student-teacher-transfer-learning","title":"BridgeNets: Student-Teacher Transfer Learning Based on Recursive Neural Networks and its Application to Distant Speech Recognition","date":"2017-10-27","arxiv_id":"1710.10224","repositories_listed":0,"syntology":null},{"url":null,"slug":"syntactic-and-semantic-features-for-code","title":"Syntactic and Semantic Features For Code-Switching Factored Language Models","date":"2017-10-04","arxiv_id":"1710.01809","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-wav2text-with-feature","title":"Attention-based Wav2Text with Feature Transfer Learning","date":"2017-09-22","arxiv_id":"1709.07814","repositories_listed":0,"syntology":null},{"url":null,"slug":"werd-using-social-text-spelling-variants-for","title":"WERd: Using Social Text Spelling Variants for Evaluating Dialectal Speech Recognition","date":"2017-09-21","arxiv_id":"1709.07484","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-recorded-debating-dataset","title":"A Recorded Debating Dataset","date":"2017-09-19","arxiv_id":"1709.06438","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-modeling-with-highway-lstm","title":"Language Modeling with Highway LSTM","date":"2017-09-19","arxiv_id":"1709.06436","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-waveform-utterance-enhancement-for","title":"End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks","date":"2017-09-12","arxiv_id":"1709.03658","repositories_listed":0,"syntology":null},{"url":null,"slug":"amharic-english-speech-translation-in-tourism","title":"Amharic-English Speech Translation in Tourism Domain","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-asr-lattices-with-pos-tags-for","title":"Enriching ASR Lattices with POS Tags for Dependency Parsing","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"c9d87d35f8af1782fa07c5c1dc2446eecd44dbb438464e35fe76859af1df40c6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}