{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-to-text/papers/4","list_of":"/task/speech-to-text","task":"Speech-to-Text","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":4,"pages_in_order":5,"rows_per_page":100,"rows":[301,400],"of":403,"counts":{"archive_papers_tagged":403,"with_a_code_link":129,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":403,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":18,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":18,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speech-to-text","prev":"/task/speech-to-text/papers/3","next":"/task/speech-to-text/papers/5","papers":[{"url":null,"slug":"decision-attentive-regularization-to-improve","title":"Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems","date":"2021-10-13","arxiv_id":"2110.15729","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-on-non-autoregressive","title":"A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation","date":"2021-10-11","arxiv_id":"2110.05249","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-testing-of-ai-models","title":"Automated Testing of AI Models","date":"2021-10-07","arxiv_id":"2110.03320","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-and-opportunities-of-speech","title":"Challenges and Opportunities of Speech Recognition for Bengali Language","date":"2021-09-27","arxiv_id":"2109.13217","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-interval-retrieval-using-convolutional","title":"Audio Interval Retrieval using Convolutional Neural Networks","date":"2021-09-21","arxiv_id":"2109.09906","repositories_listed":0,"syntology":null},{"url":null,"slug":"wav-bert-cooperative-acoustic-and-linguistic","title":"Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition","date":"2021-09-19","arxiv_id":"2109.09161","repositories_listed":0,"syntology":null},{"url":null,"slug":"with-one-voice-composing-a-travel-voice","title":"With One Voice: Composing a Travel Voice Assistant from Re-purposed Models","date":"2021-08-04","arxiv_id":"2108.11463","repositories_listed":0,"syntology":null},{"url":null,"slug":"bts-back-transcription-for-speech-to-text","title":"BTS: Back TranScription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"corpus-creation-and-evaluation-for-speech-to","title":"Corpus Creation and Evaluation for Speech-to-Text and Speech Translation","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-speech-translation-from","title":"Multilingual Speech Translation from Efficient Finetuning of Pretrained Models","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-speech-translation-by-understanding","title":"Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task","date":"2021-07-12","arxiv_id":"2107.05782","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ustc-nelslip-systems-for-simultaneous","title":"The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021","date":"2021-07-01","arxiv_id":"2107.00279","repositories_listed":0,"syntology":null},{"url":null,"slug":"pay-better-attention-to-attention-head","title":"Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling","date":"2021-06-21","arxiv_id":"2106.10840","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-simultaneous-speech-to-text","title":"Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR","date":"2021-06-11","arxiv_id":"2106.06636","repositories_listed":0,"syntology":null},{"url":"/paper/task-aware-multi-task-learning-for-speech-to","slug":"task-aware-multi-task-learning-for-speech-to","title":"TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS","date":"2021-06-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-design-of-strategic-task","title":"On the Design of Strategic Task Recommendations for Sustainable Crowdsourcing-Based Content Moderation","date":"2021-06-04","arxiv_id":"2106.02708","repositories_listed":0,"syntology":null},{"url":null,"slug":"findings-of-the-second-workshop-on-automatic","title":"Findings of the Second Workshop on Automatic Simultaneous Translation","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"worldly-wise-wow-cross-lingual-knowledge","title":"Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-shall-we-do-with-an-hour-of-data-speech","title":"What shall we do with an hour of data? Speech recognition for the un- and under-served languages of Common Voice","date":"2021-05-10","arxiv_id":"2105.04674","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-benchmarking-on-cloud-based-speech-to-text","title":"A Benchmarking on Cloud based Speech-To-Text Services for French Speech and Background Noise Effect","date":"2021-05-07","arxiv_id":"2105.03409","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-between-streaming-and-non","title":"Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models","date":"2021-04-25","arxiv_id":"2104.14346","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-synchronous-speech-to-text-alignment","title":"Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers","date":"2021-04-21","arxiv_id":"2104.10328","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-discriminator-sobolev-defense-gan","title":"Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems","date":"2021-03-15","arxiv_id":"2103.08086","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-speech-to-text-adversarial","title":"Towards Robust Speech-to-Text Adversarial Attack","date":"2021-03-15","arxiv_id":"2103.08095","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-the-evaluation-of-simultaneous-speech","title":"Towards the evaluation of automatic simultaneous speech translation from a communicative perspective","date":"2021-03-15","arxiv_id":"2103.08364","repositories_listed":0,"syntology":null},{"url":null,"slug":"inductive-biases-pretraining-and-fine-tuning","title":"Inductive biases, pretraining and fine-tuning jointly account for brain responses to speech","date":"2021-02-25","arxiv_id":"2103.01032","repositories_listed":0,"syntology":null},{"url":null,"slug":"nuva-a-naming-utterance-verifier-for-aphasia","title":"NUVA: A Naming Utterance Verifier for Aphasia Treatment","date":"2021-02-10","arxiv_id":"2102.05408","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-adversarial-examples-attacks-using","title":"Audio Adversarial Examples: Attacks Using Vocal Masks","date":"2021-02-04","arxiv_id":"2102.02417","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-networks-to-predict-customer","title":"Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center","date":"2021-01-31","arxiv_id":"2102.00420","repositories_listed":0,"syntology":null},{"url":null,"slug":"bcn2brno-asr-system-fusion-for-albayzin-2020","title":"BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge","date":"2021-01-29","arxiv_id":"2101.12729","repositories_listed":0,"syntology":null},{"url":null,"slug":"wer-bert-automatic-wer-estimation-with-bert","title":"WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm","date":"2021-01-14","arxiv_id":"2101.05478","repositories_listed":0,"syntology":null},{"url":"/paper/exploring-transfer-learning-for-end-to-end","slug":"exploring-transfer-learning-for-end-to-end","title":"Exploring Transfer Learning For End-to-End Spoken Language Understanding","date":"2020-12-15","arxiv_id":"2012.08549","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-domain-knowledge-to-improve","title":"Incorporating Domain Knowledge To Improve Topic Segmentation Of Long MOOC Lecture Videos","date":"2020-12-08","arxiv_id":"2012.07589","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-low-latency-asr-free-end-to-end-spoken","title":"A low latency ASR-free end to end spoken language understanding system","date":"2020-11-10","arxiv_id":"2011.04884","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectively-pretraining-a-speech-translation","title":"Effectively pretraining a speech translation decoder with Machine Translation data","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-modality-gap-for-speech-to-text","title":"Bridging the Modality Gap for Speech-to-Text Translation","date":"2020-10-28","arxiv_id":"2010.14920","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-transfer-learning-for","title":"Multilingual Speech Translation with Efficient Finetuning of Pretrained Models","date":"2020-10-24","arxiv_id":"2010.12829","repositories_listed":0,"syntology":null},{"url":null,"slug":"class-conditional-defense-gan-against-end-to","title":"Class-Conditional Defense GAN Against End-to-End Speech Attacks","date":"2020-10-22","arxiv_id":"2010.11352","repositories_listed":0,"syntology":null},{"url":null,"slug":"mam-masked-acoustic-modeling-for-end-to-end","title":"MAM: Masked Acoustic Modeling for End-to-End Speech-to-Text Translation","date":"2020-10-22","arxiv_id":"2010.11445","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-multi-task-learning-framework-to","title":"A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks","date":"2020-10-21","arxiv_id":"2010.11338","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-chinese-end-to-end-spoken-language","title":"Ensemble Chinese End-to-End Spoken Language Understanding for Abnormal Event Detection from audio stream","date":"2020-10-19","arxiv_id":"2010.09235","repositories_listed":0,"syntology":null},{"url":null,"slug":"subtitles-to-segmentation-improving-low-1","title":"Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines","date":"2020-10-19","arxiv_id":"2010.09693","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-against-neural-networks","title":"Adversarial Attacks against Neural Networks in Audio Domain: Exploiting Principal Components","date":"2020-07-14","arxiv_id":"2007.07001","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextualized-spoken-word-representations","title":"Contextualized Spoken Word Representations from Convolutional Autoencoders","date":"2020-07-06","arxiv_id":"2007.02880","repositories_listed":0,"syntology":null},{"url":"/paper/end-to-end-offline-speech-translation-system","slug":"end-to-end-offline-speech-translation-system","title":"End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-simultaneous-translation-system","title":"End-to-End Simultaneous Translation System for IWSLT2020 Using Modality Agnostic Meta-Learning","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simulspeech-end-to-end-simultaneous-speech-to","title":"SimulSpeech: End-to-End Simultaneous Speech to Text Translation","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-representations-improve-end","title":"Self-Supervised Representations Improve End-to-End Speech Translation","date":"2020-06-22","arxiv_id":"2006.12124","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-of-end-to-end-asr-for-openstt","title":"Exploration of End-to-End ASR for OpenSTT -- Russian Open Speech-to-Text Dataset","date":"2020-06-15","arxiv_id":"2006.08274","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cross-lingual-transfer-learning-for","title":"Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation","date":"2020-06-09","arxiv_id":"2006.05474","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-trac-consortium-for-end-to-end-and","title":"ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020","date":"2020-05-24","arxiv_id":"2005.11861","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-to-text-adaptation-towards-an","title":"Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation","date":"2020-05-17","arxiv_id":"2005.08213","repositories_listed":0,"syntology":null},{"url":null,"slug":"crossing-the-ssh-bridge-with-interview-data","title":"Crossing the SSH Bridge with Interview Data","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spice-a-new-open-access-corpus-of","title":"SpiCE: A New Open-Access Corpus of Conversational Bilingual Speech in Cantonese and English","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"subtitles-to-segmentation-improving-low","title":"Subtitles to Segmentation: Improving Low-Resource Speech-to-TextTranslation Pipelines","date":"2020-05-01","arxiv_id":null,"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":"cloud-based-face-and-speech-recognition-for","title":"Cloud-Based Face and Speech Recognition for Access Control Applications","date":"2020-04-23","arxiv_id":"2004.11168","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnings-from-technological-interventions-in","title":"Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi","date":"2020-04-21","arxiv_id":"2004.10270","repositories_listed":0,"syntology":null},{"url":null,"slug":"speak2label-using-domain-knowledge-for","title":"Speak2Label: Using Domain Knowledge for Creating a Large Scale Driver Gaze Zone Estimation Dataset","date":"2020-04-13","arxiv_id":"2004.05973","repositories_listed":0,"syntology":null},{"url":"/paper/the-spotify-podcasts-dataset","slug":"the-spotify-podcasts-dataset","title":"The Spotify Podcast Dataset","date":"2020-04-08","arxiv_id":"2004.04270","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-based-embedded-speech-to-text-using","title":"A.I. based Embedded Speech to Text Using Deepspeech","date":"2020-02-25","arxiv_id":"2002.12830","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-on-end-to-end-speech-to","title":"A Comparative Study on End-to-end Speech to Text Translation","date":"2019-11-20","arxiv_id":"1911.08870","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":"/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":"the-iwslt-2019-evaluation-campaign","title":"The IWSLT 2019 Evaluation Campaign","date":"2019-11-01","arxiv_id":null,"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":"instance-based-model-adaptation-for-direct","title":"Instance-Based Model Adaptation For Direct Speech Translation","date":"2019-10-23","arxiv_id":"1910.10663","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":"darts-dialectal-arabic-transcription-system","title":"DARTS: Dialectal Arabic Transcription System","date":"2019-09-26","arxiv_id":"1909.12163","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifying-topics-in-speech-when-all-you","title":"Cross-lingual topic prediction for speech using translations","date":"2019-08-29","arxiv_id":"1908.11425","repositories_listed":0,"syntology":null},{"url":"/paper/ims-speech-a-speech-to-text-tool","slug":"ims-speech-a-speech-to-text-tool","title":"IMS-Speech: A Speech to Text Tool","date":"2019-08-13","arxiv_id":"1908.04743","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-transformer-for-end-to-end-speech","title":"Enhancing Transformer for End-to-end Speech-to-Text Translation","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-utility-of-visual-context-in","title":"Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions","date":"2019-06-30","arxiv_id":"1907.00477","repositories_listed":0,"syntology":null},{"url":null,"slug":"telephonetic-making-neural-language-models","title":"Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise","date":"2019-06-13","arxiv_id":"1906.05678","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-interactions-in-autonomous","title":"Natural Language Interactions in Autonomous Vehicles: Intent Detection and Slot Filling from Passenger Utterances","date":"2019-04-23","arxiv_id":"1904.10500","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepcruiser-automated-guided-testing-for","title":"DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems","date":"2018-12-13","arxiv_id":"1812.05339","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-natural-language-processing","title":"Development of Natural Language Processing Tools for Cook Islands M\\=aori","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-voice-controlled-e-commerce-web-application","title":"A Voice Controlled E-Commerce Web Application","date":"2018-11-16","arxiv_id":"1811.09688","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-weakly-supervised-data-to-improve","title":"Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation","date":"2018-11-05","arxiv_id":"1811.02050","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unsupervised-speech-to-text","title":"Towards Unsupervised Speech-to-Text Translation","date":"2018-11-04","arxiv_id":"1811.01307","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":"deep-learning-based-natural-language","title":"Deep Learning Based Natural Language Processing for End to End Speech Translation","date":"2018-08-09","arxiv_id":"1808.04459","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":"low-resource-speech-to-text-translation","title":"Low-Resource Speech-to-Text Translation","date":"2018-03-24","arxiv_id":"1803.09164","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-to-text-and-text-to-speech-recognition","title":"Speech to text and text to speech recognition systems-Areview","date":"2018-03-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-2017-kit-iwslt-speech-to-text-systems-for","title":"The 2017 KIT IWSLT Speech-to-Text Systems for English and German","date":"2017-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-features-for-context-aware-speech","title":"Visual Features for Context-Aware Speech Recognition","date":"2017-12-01","arxiv_id":"1712.00489","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-strategies-annotation-in-the-waw","title":"Interpreting Strategies Annotation in the WAW Corpus","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-end-to-end-speech-recognition","title":"Attention-Based End-to-End Speech Recognition on Voice Search","date":"2017-07-22","arxiv_id":"1707.07167","repositories_listed":0,"syntology":null},{"url":null,"slug":"polish-read-speech-corpus-for-speech-tools","title":"Polish Read Speech Corpus for Speech Tools and Services","date":"2017-06-01","arxiv_id":"1706.00245","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-of-heterogeneous-corpora-for-training","title":"Using of heterogeneous corpora for training of an ASR system","date":"2017-06-01","arxiv_id":"1706.00321","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":"the-2016-kit-iwslt-speech-to-text-systems-for","title":"The 2016 KIT IWSLT Speech-to-Text Systems for English and German","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"numerically-grounded-language-models-for","title":"Numerically Grounded Language Models for Semantic Error Correction","date":"2016-08-14","arxiv_id":"1608.04147","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dutch-dysarthric-speech-database-for","title":"A Dutch Dysarthric Speech Database for Individualized Speech Therapy Research","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lia-rag-a-system-based-on-graphs-and","title":"LIA-RAG: a system based on graphs and divergence of probabilities applied to Speech-To-Text Summarization","date":"2016-01-26","arxiv_id":"1601.07124","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-usfd-spoken-language-translation-system","title":"The USFD Spoken Language Translation System for IWSLT 2014","date":"2015-09-13","arxiv_id":"1509.03870","repositories_listed":0,"syntology":null},{"url":null,"slug":"voice-based-self-help-system-user-experience","title":"Voice based self help System: User Experience Vs Accuracy","date":"2015-04-07","arxiv_id":"1504.01496","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-recognition-web-services-for-dutch","title":"Speech Recognition Web Services for Dutch","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-in-speech-to-text-voice-analysis-of","title":"Noise in Speech-to-Text Voice: Analysis of Errors and Feasibility of Phonetic Similarity for Their Correction","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"5195ae41bc17dd4e210b0fba6dc4370aa324016a34ee3d57cdf3e10674856f71","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}