{"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/31","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":31,"pages_in_order":32,"rows_per_page":100,"rows":[3001,3100],"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/30","next":"/task/automatic-speech-recognition-2/papers/32","papers":[{"url":null,"slug":"towards-quantum-language-models","title":"Towards Quantum Language Models","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-analysis-of-dnn-hmm","title":"Information Theoretic Analysis of DNN-HMM Acoustic Modeling","date":"2017-08-29","arxiv_id":"1709.01144","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-residual-lstm-architecture-for","title":"An Improved Residual LSTM Architecture for Acoustic Modeling","date":"2017-08-17","arxiv_id":"1708.05682","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialogue-act-segmentation-for-vietnamese","title":"Dialogue Act Segmentation for Vietnamese Human-Human Conversational Texts","date":"2017-08-16","arxiv_id":"1708.04765","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-joint-modeling-in-unsupervised","title":"Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition","date":"2017-07-21","arxiv_id":"1707.07048","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-accurate-oov-decoder-on-high-level","title":"Fast and Accurate OOV Decoder on High-Level Features","date":"2017-07-19","arxiv_id":"1707.06195","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-channel-multi-talker-speech","title":"Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training","date":"2017-07-19","arxiv_id":"1707.06527","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-for-robust","title":"Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation","date":"2017-07-19","arxiv_id":"1707.06265","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoding-word-confusion-networks-with","title":"Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking","date":"2017-07-18","arxiv_id":"1707.05853","repositories_listed":0,"syntology":null},{"url":null,"slug":"listening-while-speaking-speech-chain-by-deep","title":"Listening while Speaking: Speech Chain by Deep Learning","date":"2017-07-16","arxiv_id":"1707.04879","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-with-very-large","title":"Automatic Speech Recognition with Very Large Conversational Finnish and Estonian Vocabularies","date":"2017-07-13","arxiv_id":"1707.04227","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-causes-of-reformulation-in","title":"Predicting Causes of Reformulation in Intelligent Assistants","date":"2017-07-13","arxiv_id":"1707.03968","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-quality-estimation-for-asr-system","title":"Automatic Quality Estimation for ASR System Combination","date":"2017-06-22","arxiv_id":"1706.07238","repositories_listed":0,"syntology":null},{"url":null,"slug":"modelling-prosodic-structure-using-artificial","title":"Modelling prosodic structure using Artificial Neural Networks","date":"2017-06-13","arxiv_id":"1706.03952","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-neural-networks-for-subvocal","title":"End-to-end neural networks for subvocal speech recognition","date":"2017-06-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-environmentally-robust","title":"Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments","date":"2017-05-30","arxiv_id":"1705.10874","repositories_listed":0,"syntology":null},{"url":null,"slug":"asr-error-management-for-improving-spoken","title":"ASR error management for improving spoken language understanding","date":"2017-05-26","arxiv_id":"1705.09515","repositories_listed":0,"syntology":null},{"url":null,"slug":"anti-spoofing-methods-for-automatic","title":"Anti-spoofing Methods for Automatic SpeakerVerification System","date":"2017-05-24","arxiv_id":"1705.08865","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-monotonic-attention-mechanism-for-end","title":"Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing","date":"2017-05-23","arxiv_id":"1705.08091","repositories_listed":0,"syntology":null},{"url":null,"slug":"use-of-knowledge-graph-in-rescoring-the-n","title":"Use of Knowledge Graph in Rescoring the N-Best List in Automatic Speech Recognition","date":"2017-05-22","arxiv_id":"1705.08018","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-model-of-a-pronunciation-lexicon","title":"A Generative Model of a Pronunciation Lexicon for Hindi","date":"2017-05-06","arxiv_id":"1705.02452","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-viseme-vocabulary-construction-to","title":"Automatic Viseme Vocabulary Construction to Enhance Continuous Lip-reading","date":"2017-04-26","arxiv_id":"1704.08035","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-estimating-the-upper-bound-of-visual","title":"Towards Estimating the Upper Bound of Visual-Speech Recognition: The Visual Lip-Reading Feasibility Database","date":"2017-04-26","arxiv_id":"1704.08028","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-automatic-speech-recognition","title":"An enhanced automatic speech recognition system for Arabic","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aoh-ive-heard-that-before-modelling-own","title":"``Oh, I've Heard That Before'': Modelling Own-Dialect Bias After Perceptual Learning by Weighting Training Data","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cassandra-a-multipurpose-configurable-voice","title":"CASSANDRA: A multipurpose configurable voice-enabled human-computer-interface","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-and-dialect-bias-in-youtubes-automatic","title":"Gender and Dialect Bias in YouTube's Automatic Captions","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-summa-platform-prototype","title":"The SUMMA Platform Prototype","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-similarity-functions-for","title":"Learning Similarity Functions for Pronunciation Variations","date":"2017-03-28","arxiv_id":"1703.09817","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-acoustics-to-word-models-for-english","title":"Direct Acoustics-to-Word Models for English Conversational Speech Recognition","date":"2017-03-22","arxiv_id":"1703.07754","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-multi-talker-speech-with","title":"Recognizing Multi-talker Speech with Permutation Invariant Training","date":"2017-03-22","arxiv_id":"1704.01985","repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-identification-for-speech-without-asr","title":"Topic Identification for Speech without ASR","date":"2017-03-22","arxiv_id":"1703.07476","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-learning-of-correlated-sequence","title":"Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks","date":"2017-03-14","arxiv_id":"1703.04650","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-convolutional-ctc-networks-for","title":"Residual Convolutional CTC Networks for Automatic Speech Recognition","date":"2017-02-24","arxiv_id":"1702.07793","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-relevance-of-auditory-based-gabor","title":"On the Relevance of Auditory-Based Gabor Features for Deep Learning in Automatic Speech Recognition","date":"2017-02-14","arxiv_id":"1702.04333","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-speech-to-text-translation-without","title":"Towards speech-to-text translation without speech recognition","date":"2017-02-13","arxiv_id":"1702.03856","repositories_listed":0,"syntology":null},{"url":null,"slug":"structural-analysis-of-hindi-phonetics-and-a","title":"Structural Analysis of Hindi Phonetics and A Method for Extraction of Phonetically Rich Sentences from a Very Large Hindi Text Corpus","date":"2017-01-30","arxiv_id":"1701.08655","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-word-like-units-from-joint-audio","title":"Learning Word-Like Units from Joint Audio-Visual Analysis","date":"2017-01-25","arxiv_id":"1701.07481","repositories_listed":0,"syntology":null},{"url":null,"slug":"lyrics-to-audio-alignment-by-unsupervised","title":"Lyrics-to-Audio Alignment by Unsupervised Discovery of Repetitive Patterns in Vowel Acoustics","date":"2017-01-21","arxiv_id":"1701.06078","repositories_listed":0,"syntology":null},{"url":null,"slug":"auxiliary-multimodal-lstm-for-audio-visual","title":"Auxiliary Multimodal LSTM for Audio-visual Speech Recognition and Lipreading","date":"2017-01-16","arxiv_id":"1701.04224","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-asr-free-keyword-search-from","title":"End-to-End ASR-free Keyword Search from Speech","date":"2017-01-13","arxiv_id":"1701.04313","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-of-deep-neural-networks","title":"Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition","date":"2017-01-10","arxiv_id":"1701.02477","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-language-level-information-into","title":"Incorporating Language Level Information into Acoustic Models","date":"2016-12-14","arxiv_id":"1612.04744","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-deep-stacking-networks-for-speech","title":"Recurrent Deep Stacking Networks for Speech Recognition","date":"2016-12-14","arxiv_id":"1612.04675","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-automatic-speech-recognition","title":"Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures","date":"2016-12-13","arxiv_id":"1612.03990","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-decoding-and-language-model","title":"Towards better decoding and language model integration in sequence to sequence models","date":"2016-12-08","arxiv_id":"1612.02695","repositories_listed":0,"syntology":null},{"url":"/paper/a-non-expert-kaldi-recipe-for-vietnamese","slug":"a-non-expert-kaldi-recipe-for-vietnamese","title":"A non-expert Kaldi recipe for Vietnamese Speech Recognition System","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"arabic-language-weka-based-dialect-classifier","title":"Arabic Language WEKA-Based Dialect Classifier for Arabic Automatic Speech Recognition Transcripts","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-speech-unit-delimitation-in-spoken","title":"Automated speech-unit delimitation in spoken learner English","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-errors-as-a","title":"Automatic Speech Recognition Errors as a Predictor of L2 Listening Difficulties","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-grapheme-to-phoneme-conversion","title":"Comparison of Grapheme-to-Phoneme Conversion Methods on a Myanmar Pronunciation Dictionary","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"racai-entry-for-the-iwslt-2016-shared-task","title":"RACAI Entry for the IWSLT 2016 Shared Task","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-iwslt-2016-evaluation-campaign","title":"The IWSLT 2016 Evaluation Campaign","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"invariant-representations-for-noisy-speech","title":"Invariant Representations for Noisy Speech Recognition","date":"2016-11-27","arxiv_id":"1612.01928","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-recurrent-convolutional-neural-network","title":"Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition","date":"2016-11-22","arxiv_id":"1611.07174","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-speech-recognition-using-deep","title":"Audio Visual Speech Recognition using Deep Recurrent Neural Networks","date":"2016-11-09","arxiv_id":"1611.02879","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-recognition-of-child-speech-for","title":"Automatic recognition of child speech for robotic applications in noisy environments","date":"2016-11-08","arxiv_id":"1611.02695","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-transition-based-dependency-parsing-and","title":"Joint Transition-based Dependency Parsing and Disfluency Detection for Automatic Speech Recognition Texts","date":"2016-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-sentence-and-context","title":"Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding","date":"2016-10-13","arxiv_id":"1610.04120","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semantic-analyzer-for-the-comprehension-of","title":"A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech","date":"2016-10-08","arxiv_id":"1610.02493","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-of-computational-processing-of","title":"Challenges of Computational Processing of Code-Switching","date":"2016-10-07","arxiv_id":"1610.02213","repositories_listed":0,"syntology":null},{"url":null,"slug":"monaural-multi-talker-speech-recognition","title":"Monaural Multi-Talker Speech Recognition using Factorial Speech Processing Models","date":"2016-10-05","arxiv_id":"1610.01367","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-learning-with-sparse","title":"Semi-supervised Learning with Sparse Autoencoders in Phone Classification","date":"2016-10-03","arxiv_id":"1610.00520","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-visualization-for-gated-recurrent","title":"Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition","date":"2016-09-28","arxiv_id":"1609.08789","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimally-supervised-written-to-spoken-text","title":"Minimally Supervised Written-to-Spoken Text Normalization","date":"2016-09-21","arxiv_id":"1609.06649","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adaptive-psychoacoustic-model-for","title":"An Adaptive Psychoacoustic Model for Automatic Speech Recognition","date":"2016-09-14","arxiv_id":"1609.04417","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-teacher-questions-using-automatic","title":"Identifying Teacher Questions Using Automatic Speech Recognition in Classrooms","date":"2016-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transcrater-a-tool-for-automatic-speech","title":"TranscRater: a Tool for Automatic Speech Recognition Quality Estimation","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-human-language-technology-to-human","title":"From Human Language Technology to Human Language Science","date":"2016-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-deep-bidirectional","title":"A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition","date":"2016-06-22","arxiv_id":"1606.06871","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-curriculum-learning-method-for-improved","title":"A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition","date":"2016-06-22","arxiv_id":"1606.06864","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-manifold-regularized-deep-neural","title":"Graph based manifold regularized deep neural networks for automatic speech recognition","date":"2016-06-19","arxiv_id":"1606.05925","repositories_listed":0,"syntology":null},{"url":null,"slug":"calibration-of-phone-likelihoods-in-automatic","title":"Calibration of Phone Likelihoods in Automatic Speech Recognition","date":"2016-06-14","arxiv_id":"1606.04317","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-variance-and-performance-evaluation","title":"Training variance and performance evaluation of neural networks in speech","date":"2016-06-14","arxiv_id":"1606.04521","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ibm-speaker-recognition-system-recent","title":"The IBM Speaker Recognition System: Recent Advances and Error Analysis","date":"2016-05-05","arxiv_id":"1605.01635","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-analysis-of-crowdsourced","title":"A Comparative Analysis of Crowdsourced Natural Language Corpora for Spoken Dialog Systems","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-corpus-of-read-and-spontaneous-upper-saxon","title":"A Corpus of Read and Spontaneous Upper Saxon German Speech for ASR Evaluation","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-a-speech-corpus-for-the-development","title":"Designing a Speech Corpus for the Development and Evaluation of Dictation Systems in Latvian","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"endangered-language-documentation","title":"Endangered Language Documentation: Bootstrapping a Chatino Speech Corpus, Forced Aligner, ASR","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-corilga-introducing-the-automatic","title":"Enhanced CORILGA: Introducing the Automatic Phonetic Alignment Tool for Continuous Speech","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"falling-silent-lost-for-words-tracing","title":"Falling silent, lost for words ... Tracing personal involvement in interviews with Dutch war veterans","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-task-pertinent-sorted-error-lists","title":"Generating Task-Pertinent sorted Error Lists for Speech Recognition","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joining-in-type-humanoid-robot-assisted","title":"Joining-in-type Humanoid Robot Assisted Language Learning System","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"operational-assessment-of-keyword-search-on","title":"Operational Assessment of Keyword Search on Oral History","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dirha-portuguese-corpus-a-comparison-of","title":"The DIRHA Portuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data.","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ilmt-s2s-corpus-a-a-multimodal","title":"The ILMT-s2s Corpus ― A Multimodal Interlingual Map Task Corpus","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-si-tedx-um-speech-database-a-new","title":"The SI TEDx-UM speech database: a new Slovenian Spoken Language Resource","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automatic-transcription-of-ilse-a-an","title":"Towards Automatic Transcription of ILSE ― an Interdisciplinary Longitudinal Study of Adult Development and Aging","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-the-ted-talks-to-evaluate-spoken-post","title":"Using the TED Talks to Evaluate Spoken Post-editing of Machine Translation","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-frequency-cepstral-coefficients-for","title":"Adaptive Frequency Cepstral Coefficients for Word Mispronunciation Detection","date":"2016-02-25","arxiv_id":"1602.08132","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ibm-2016-speaker-recognition-system","title":"The IBM 2016 Speaker Recognition System","date":"2016-02-23","arxiv_id":"1602.07291","repositories_listed":0,"syntology":null},{"url":null,"slug":"signer-independent-fingerspelling-recognition","title":"Signer-independent Fingerspelling Recognition with Deep Neural Network Adaptation","date":"2016-02-13","arxiv_id":"1602.04278","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-recognition-of-element-classes-and","title":"Automatic recognition of element classes and boundaries in the birdsong with variable sequences","date":"2016-01-23","arxiv_id":"1601.06248","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-2015-sheffield-system-for-transcription","title":"The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media","date":"2015-12-21","arxiv_id":"1512.06643","repositories_listed":0,"syntology":null},{"url":null,"slug":"spoken-language-translation-for-polish","title":"Spoken Language Translation for Polish","date":"2015-11-24","arxiv_id":"1511.07788","repositories_listed":0,"syntology":null},{"url":null,"slug":"blending-lstms-into-cnns","title":"Blending LSTMs into CNNs","date":"2015-11-19","arxiv_id":"1511.06433","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancements-in-statistical-spoken-language","title":"Enhancements in statistical spoken language translation by de-normalization of ASR results","date":"2015-11-18","arxiv_id":"1511.09392","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-dirichlet-allocation-based","title":"Latent Dirichlet Allocation Based Organisation of Broadcast Media Archives for Deep Neural Network Adaptation","date":"2015-11-16","arxiv_id":"1511.05076","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-structured-deep-neural-network-for-1","title":"Towards Structured Deep Neural Network for Automatic Speech Recognition","date":"2015-11-08","arxiv_id":"1511.02506","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-speech-recognition-using-neural","title":"類神經網路訓練結合環境群集及專家混合系統於強健性語音辨識(Automatic Speech Recognition using Neural Network based Acoustic Model with the Environment Clustering and Mixture of Experts Algorithms) [In Chinese]","date":"2015-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"c8b62b9411000e33ba7336fa44f0c312b4aeafca552672ce3eb399b45f7730c7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}