Sources
Preprint
133 sources, newest first. Open one to see the facts taken from it and the link to the original.
- Are Caption Metrics Broken? Latency, Deaf and Hard of Hearing User Ratings, and Bias across TechnologiesBernard Thompson et al., arXiv (preprint), accepted for ACM ASSETS 2026, 2026 · 3 facts
- Conversational Speech Reveals Structural Robustness Failures in SpeechLLM BackbonesMaria Teleki et al., arXiv, 2026 · 1 facts
- Dialect and Gender Bias in YouTube's Spanish Captioning SystemIris Dania Jimenez and Christoph Kern, arXiv (Computation and Language, cs.CL), preprint 2602.24002, 2026 · 3 facts
- End-to-End Joint ASR and Speaker Role Diarization with Child-Adult InteractionsAnfeng Xu et al., arXiv, 2026 · 1 facts
- Factors affecting ASR performance: A study using state of the art ASR models in Indic LanguagesAgneedh Basu et al., arXiv preprint, 2026 · 1 facts
- How LLMs Distort Our Written LanguageMarwa Abdulhai et al., arXiv, 2026 · 2 facts
- Lost in Transcription: How Speech-to-Text Errors Derail Code UnderstandingJayant Havare et al., arXiv, 2026 · 2 facts
- PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech TranslationGiang Son Nguyen et al., arXiv, 2026 · 2 facts
- Quality of Automatic Speech Recognition: Polish Language case study, from Wav2Vec to Scribe ElevenLabsMarcin Pietroń et al., Pietron et al., 2026 · 1 facts
- Say What? Examining Text and Voice Input Modalities for Prompt-Based Programming in Computing EducationKaitlin Riegel et al., arXiv, 2026 · 2 facts
- Sorry, I Didn’t Catch That: How Speech Models Miss What Matters MostKaitlyn Zhou et al., arXiv, 2026 · 1 facts
- Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WERFelix Akeret, arXiv (Computation and Language), 2026 · 1 facts
- The Hidden Cost of Digits: Number Normalization and WER in ASR SystemsStanisław Kacprzak and Mieszko Fraś, arXiv (eess.AS), AGH University of Krakow, 2026 · 2 facts
- Towards Orthographically-Informed Evaluation of Speech Recognition Systems for Indian LanguagesKaushal Santosh Bhogale et al., arXiv preprint (AI4Bharat, IIT Madras), 2026 · 1 facts
- Towards Robust Dysarthric Speech Recognition: LLM-Agent Post-ASR Correction Beyond WERXiuwen Zheng et al., arXiv (ICASSP 2026), 2026 · 2 facts
- τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World DomainsSoham Ray et al., arXiv, 2026 · 3 facts
- Acoustically Precise Hesitation Tagging Is Essential for End-to-End Verbatim Transcription SystemsJhen-Ke Lin et al., arXiv (SLaTE 2025 workshop), 2025 · 3 facts
- Automatic Speech Recognition for Non-Native English: Accuracy and Disfluency HandlingMichael McGuire, arXiv, 2025 · 4 facts
- Benchmarking Automatic Speech Recognition Models for African LanguagesarXiv, 2025 · 1 facts
- Brain-to-Text Decoding: A Non-invasive Approach via TypingJarod Levy et al., arXiv (preprint), 2025 · 3 facts
- CAMÕES: A Comprehensive Automatic Speech Recognition Benchmark for European PortugueseCarlos Carvalho et al., arXiv, 2025 · 2 facts
- Causal Analysis of ASR Errors for Children: Quantifying the Impact of Physiological, Cognitive, and Extrinsic FactorsVishwanath Pratap Singh et al., arXiv, 2025 · 1 facts
- Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature ReviewMaha Tufail Agro et al., arXiv (accepted at LREC 2026), 2025 · 1 facts
- Code-switching Speech Recognition Under the Lens: Model- and Data-Centric PerspectivesHexin Liu et al., arXiv, 2025 · 2 facts
- CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech RecognitionJiaming Zhou et al., arXiv, 2025 · 1 facts
- Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024Nuria Alina Chandra et al., arXiv, 2025 · 3 facts
- Effects of Prompt Length on Domain-specific Tasks for Large Language ModelsQibang Liu et al., arXiv preprint 2502.14255, 2025 · 2 facts
- Enriching Historical Records: An OCR and AI-Driven Approach for Database IntegrationZahra Abedi, arXiv, 2025 · 2 facts
- Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech RecognitionYuan Tseng et al., arXiv (Audio and Speech Processing), 2025 · 2 facts
- EvolveCaptions: Empowering DHH Users Through Real-Time Collaborative CaptioningLiang-Yuan Wu and Dhruv Jain, arXiv (preprint), 2025 · 1 facts
- First Steps Towards Voice Anonymization for Code-Switching SpeechSarina Meyer et al., arXiv, 2025 · 2 facts
- Hebrew Diacritics Restoration using Visual RepresentationYair Elboher and Yuval Pinter, arXiv, 2025 · 1 facts
- Investigation of Whisper ASR Hallucinations Induced by Non-Speech AudioMateusz Barański et al., arXiv (accepted for IEEE ICASSP 2025), 2025 · 1 facts
- LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic ContextNatsuo Yamashita et al., arXiv (accepted by INTERSPEECH 2025), 2025 · 2 facts
- Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ LanguagesOmnilingual ASR team, arXiv, 2025 · 2 facts
- Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition EvaluationHugging Face and collaborators, arXiv, 2025 · 15 facts
- Open ASR Leaderboard: Towards Reproducible and Transparent Speech Recognition EvaluationHugging Face and collaborators, arXiv, 2025 · 3 facts
- Out of the Box, into the Clinic? Evaluating State-of-the-Art ASR for Clinical Applications for Older AdultsBram van Dijk et al., arXiv (forthcoming in the HCINLP workshop proceedings at EMNLP), 2025 · 1 facts
- Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral NarrativesChristiaan Jacobs et al., arXiv (Stellenbosch University and University of Edinburgh), 2025 · 2 facts
- Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and SentencesarXiv, 2025 · 2 facts
- VoiceAgentBench: Are Voice Assistants ready for agentic tasks?Dhruv Jain et al., arXiv, 2025 · 4 facts
- VoxtralMistral AI, arXiv (Audio and Speech Processing), 2025 · 8 facts
- Whisper Has an Internal Word AlignerSung-Lin Yeh et al., arXiv (ASRU 2025), 2025 · 2 facts
- WhisperD: Dementia Speech Recognition and Filler Word Detection with WhisperEmmanuel Akinrintoyo et al., arXiv, 2025 · 1 facts
- Zero-Shot Context-Aware ASR for Diverse Arabic VarietiesBashar Talafha et al., arXiv, 2025 · 1 facts
- Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and TamilNevidu Jayatilleke, arXiv, 2025 · 1 facts
- An accurate and rapidly calibrating speech neuroprosthesisNicholas S. Card et al., medRxiv preprint, deposited in PubMed Central (later published in the New England Journal of Medicine, 2024), 2024 · 3 facts
- ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at ScaleXin Wang et al., arXiv (ASVspoof 5 Workshop, Interspeech 2024 satellite), 2024 · 1 facts
- Automatically Detecting Confusion and Conflict During Collaborative Learning Using Linguistic, Prosodic, and Facial CuesYingbo Ma et al., arXiv, 2024 · 1 facts
- Breaking Down Power Barriers in On-Device Streaming ASR: Insights and SolutionsYang Li et al., arXiv (industry track of NAACL 2025, per the arXiv comments), 2024 · 1 facts
- Careless Whisper: Speech-to-Text Hallucination HarmsAllison Koenecke et al., arXiv (ACM FAccT 2024), 2024 · 3 facts
- Delving into LLM-assisted writing in biomedical publications through excess vocabularyDmitry Kobak et al., arXiv, 2024 · 1 facts
- Efficient Adaptation of Multilingual Models for Japanese ASRMark Bajo et al., arXiv, 2024 · 2 facts
- End-to-End Transformer-based Automatic Speech Recognition for Northern Kurdish: A Pioneering ApproachAbdulhady Abas Abdullah et al., arXiv, 2024 · 1 facts
- Evaluating OpenAI's Whisper ASR: Performance analysis across diverse accents and speaker traitsCalbert Graham and Nathan Roll, Cambridge Open Engage (preprint); published in JASA Express Letters, 2024, 2024 · 1 facts
- Exploring the Impact of Word Prediction Assistive Features on Smartphone Keyboards for Blind UsersMrim M. Alnfiai and Muhammad Ashad Kabir, arXiv preprint (later journal article), 2024 · 5 facts
- Findings of the 2024 Mandarin Stuttering Event Detection and Automatic Speech Recognition ChallengeHongfei Xue et al., arXiv (eess.AS), 2024 · 1 facts
- IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian LanguagesTahir Javed et al., arXiv preprint (AI4Bharat, IIT Madras), 2024 · 2 facts
- LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR SystemsTahir Javed et al., arXiv preprint (AI4Bharat, IIT Madras), 2024 · 3 facts
- Leveraging Self-Supervised Models for Automatic Whispered Speech RecognitionAref Farhadipour et al., arXiv (Electrical Engineering and Systems Science, Audio and Speech Processing), 2024 · 1 facts
- Measuring the Accuracy of Automatic Speech Recognition SolutionsKorbinian Kuhn et al., arXiv (preprint), 2024 · 4 facts
- Measuring the Accuracy of Automatic Speech Recognition SolutionsKorbinian Kuhn et al., arXiv (cs.CL), preprint, 2024 · 3 facts
- Measuring the Accuracy of Automatic Speech Recognition Solutions (HTML version)Korbinian Kuhn et al., arXiv, 2024 · 5 facts
- Moshi: a speech-text foundation model for real-time dialogueAlexandre Défossez and and colleagues at Kyutai, arXiv (Kyutai), 2024 · 4 facts
- Noise Masking Attacks and Defenses for Pretrained Speech ModelsMatthew Jagielski et al., arXiv, 2024 · 2 facts
- Open Universal Arabic ASR LeaderboardYingzhi Wang et al., arXiv, 2024 · 1 facts
- Reasoning Robustness of LLMs to Adversarial Typographical ErrorsEsther Gan et al., arXiv preprint 2411.05345, 2024 · 2 facts
- Retrieval Augmented Correction of Named Entity Speech Recognition ErrorsErnest Pusateri and et al. (nine authors in total), arXiv, 2024 · 2 facts
- Speech Synthesis and Pronunciation TeachingWaris Quamer et al., The Encyclopedia of Applied Linguistics, 2nd edition (in press), author preprint, 2024 · 1 facts
- Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion NetworksKevin Everson et al., arXiv preprint 2401.02921, 2024 · 1 facts
- Using Confidence Scores to Improve Eyes-free Detection of Speech Recognition ErrorsSadia Nowrin and Keith Vertanen, arXiv, 2024 · 2 facts
- WER We Stand: Benchmarking Urdu ASR ModelsSamee Arif et al., arXiv, 2024 · 1 facts
- Attention-Guided Adaptation for Code-Switching Speech RecognitionBobbi Aditya et al., arXiv, 2023 · 2 facts
- Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic ModelingLucas Rafael Stefanel Gris et al., arXiv (book chapter), 2023 · 6 facts
- Experimental Evidence on the Productivity Effects of Generative Artificial Intelligence (working paper)Shakked Noy and Whitney Zhang, MIT Economics working paper, 2023 · 2 facts
- GPT detectors are biased against non-native English writersWeixin Liang et al., arXiv (later published in Patterns), 2023 · 1 facts
- Honesty is the Best Policy: On the Accuracy of Apple Privacy Labels Compared to Apps' Privacy PoliciesMir Masood Ali et al., arXiv, 2023 · 2 facts
- HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language ModelsChen Chen et al., arXiv (NeurIPS 2023 dataset track), 2023 · 3 facts
- Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive EvaluationTao Fang et al., arXiv, 2023 · 1 facts
- Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. AdultsAhmed Adel Attia et al., arXiv (eess.AS), revised May 2024, 2023 · 1 facts
- Multi-stage Large Language Model Correction for Speech RecognitionJie Pu et al., arXiv, 2023 · 1 facts
- Neural Codec Language Models are Zero-Shot Text to Speech SynthesizersChengyi Wang et al., arXiv (Microsoft Research), 2023 · 1 facts
- Scalable Extraction of Training Data from (Production) Language ModelsMilad Nasr et al., arXiv, 2023 · 2 facts
- Scaling Speech Technology to 1,000+ LanguagesVineel Pratap et al., Meta AI (arXiv), 2023 · 2 facts
- Scaling Speech Technology to 1,000+ LanguagesVineel Pratap et al., arXiv, 2023 · 2 facts
- SeamlessM4T: Massively Multilingual and Multimodal Machine TranslationSeamless Communication, Meta AI (arXiv), 2023 · 4 facts
- SeamlessM4T: Massively Multilingual and Multimodal Machine Translation (full text)Seamless Communication, Meta AI (arXiv), 2023 · 4 facts
- Svarah: Evaluating English ASR Systems on Indian AccentsTahir Javed et al., arXiv, 2023 · 6 facts
- The Edinburgh International Accents of English Corpus: Towards the Democratization of English ASRRamon Sanabria et al., arXiv (accepted to IEEE ICASSP 2023), 2023 · 3 facts
- The Impact of AI on Developer Productivity: Evidence from GitHub CopilotSida Peng et al., arXiv preprint, 2023 · 1 facts
- Unintended Memorization in Large ASR Models, and How to Mitigate ItLun Wang et al., arXiv, 2023 · 1 facts
- WhisperX: Time-Accurate Speech Transcription of Long-Form AudioMax Bain et al., arXiv (cs.SD), 2023 · 1 facts
- Better Transcription of UK Supreme Court HearingsHadeel Saadany et al., arXiv (Cornell University), 2022 · 2 facts
- Does Joint Training Really Help Cascaded Speech Translation?Viet Anh Khoa Tran et al., arXiv, 2022 · 1 facts
- Earnings-22: A Practical Benchmark for Accents in the WildMiguel Del Rio et al., arXiv (Computation and Language), submitted to Interspeech 2022, 2022 · 2 facts
- FLEURS: Few-shot Learning Evaluation of Universal Representations of SpeechAlexis Conneau et al., arXiv (Computation and Language), 2022 · 1 facts
- FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech (full text)Alexis Conneau et al., arXiv (IEEE Spoken Language Technology Workshop 2022), 2022 · 1 facts
- On Word Error Rate Definitions and their Efficient Computation for Multi-Speaker Speech Recognition SystemsThilo von Neumann et al., arXiv (eess.AS), 2022 · 1 facts
- PriMock57: A Dataset Of Primary Care Mock ConsultationsarXiv, 2022 · 2 facts
- Robust Speech Recognition via Large-Scale Weak SupervisionAlec Radford et al., arXiv (eess.AS), 2022 · 9 facts
- Robust Speech Recognition via Large-Scale Weak Supervision (full text)Alec Radford et al., OpenAI (arXiv), 2022 · 63 facts
- Swiss German Speech to Text system evaluationYanick Schraner et al., arXiv (Computation and Language), 2022 · 1 facts
- Automatic punctuation restoration with BERT modelsAttila Nagy et al., arXiv, 2021 · 1 facts
- English Accent Accuracy Analysis in a State-of-the-Art Automatic Speech Recognition SystemGuillermo Cámbara et al., arXiv (2 pages, prepared for Phonetics and Phonology in Europe 2021), 2021 · 1 facts
- GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed AudioGuoguo Chen et al., arXiv, 2021 · 1 facts
- NeMo Inverse Text Normalization: From Development To ProductionYang Zhang et al., arXiv, 2021 · 2 facts
- Speaker-conversation factorial designs for diarization error analysisScott Seyfarth et al., arXiv, 2021 · 1 facts
- Common Voice: A Massively-Multilingual Speech CorpusRosana Ardila et al., arXiv (LREC 2020), 2020 · 2 facts
- Conformer: Convolution-augmented Transformer for Speech RecognitionAnmol Gulati et al., arXiv (Interspeech 2020), 2020 · 2 facts
- DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO TeamQingjian Lin et al., arXiv, 2020 · 3 facts
- KoSpeech: Open-Source Toolkit for End-to-End Korean Speech RecognitionSoohwan Kim et al., arXiv, 2020 · 1 facts
- MLS: A Large-Scale Multilingual Dataset for Speech ResearchVineel Pratap et al., arXiv (Computation and Language), 2020 · 1 facts
- wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsAlexei Baevski et al., arXiv (NeurIPS 2020), 2020 · 2 facts
- Disfluencies and Human Speech Transcription ErrorsVicky Zayats et al., arXiv, 2019 · 1 facts
- Gmail Smart Compose: Real-Time Assisted WritingMia Xu Chen et al., arXiv (presented at KDD 2019), 2019 · 1 facts
- Irrelevant speech effect in open plan offices: A laboratory studyKrist Kostallari et al., arXiv (eess.AS), preprint, 2019 · 2 facts
- Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detectionLatané Bullock et al., arXiv (submitted to ICASSP 2020), 2019 · 1 facts
- pyannote.audio: neural building blocks for speaker diarizationHervé Bredin et al., arXiv (submitted to ICASSP 2020), 2019 · 1 facts
- Streaming End-to-end Speech Recognition For Mobile DevicesYanzhang He et al., arXiv (ICASSP 2019), 2019 · 1 facts
- The Second DIHARD Diarization Challenge: Dataset, task, and baselinesNeville Ryant et al., arXiv (Interspeech 2019 challenge paper), 2019 · 2 facts
- Federated Learning for Mobile Keyboard PredictionAndrew Hard et al., arXiv, 2018 · 1 facts
- Hindi-English Code-Switching Speech CorpusGanji Sreeram et al., arXiv, 2018 · 1 facts
- Open Source Automatic Speech Recognition for GermanBenjamin Milde and Arne Köhn, arXiv (Computation and Language), 2018 · 2 facts
- Achieving Human Parity in Conversational Speech RecognitionW. Xiong et al., arXiv (Microsoft Research), 2017 · 3 facts
- English Conversational Telephone Speech Recognition by Humans and MachinesGeorge Saon et al., arXiv (cs.CL), IBM Research, 2017 · 4 facts
- Hello Edge: Keyword Spotting on MicrocontrollersYundong Zhang et al., arXiv, 2017 · 1 facts
- Realistic multi-microphone data simulation for distant speech recognitionMirco Ravanelli et al., arXiv (preprint, eess.AS), 2017 · 3 facts
- Realistic multi-microphone data simulation for distant speech recognitionarXiv preprint, 2017 · 3 facts
- Speech Recognition Challenge in the Wild: Arabic MGB-3Ahmed Ali et al., arXiv, 2017 · 2 facts
- Listen, Attend and SpellWilliam Chan et al., arXiv, 2015 · 2 facts
- Speech Recognition with Deep Recurrent Neural NetworksAlex Graves et al., arXiv (accepted for ICASSP 2013), 2013 · 1 facts
- Sequence Transduction with Recurrent Neural NetworksAlex Graves, arXiv (ICML 2012 Workshop on Representation Learning), 2012 · 1 facts
- Combined Acoustic and Pronunciation Modelling for Non-Native Speech RecognitionGhazi Bouselmi et al., arXiv, 2007 · 1 facts