{"total":73,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657,"area":null},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"area":null},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161,"area":null},{"id":"2104.01027","title":"Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training","created":"2021-04-02","cited_by_count":151,"area":null},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"area":null},{"id":"2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","created":"2021-04-05","cited_by_count":83,"area":null},{"id":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69,"area":null},{"id":"2206.00888","title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","created":"2022-06-02","cited_by_count":51,"area":null},{"id":"2401.04577","title":"Masked Audio Generation using a Single Non-Autoregressive Transformer","created":"2024-01-09","cited_by_count":50,"area":null},{"id":"2106.03143","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","created":"2021-06-06","cited_by_count":47,"area":null},{"id":"2204.02967","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","created":"2022-04-06","cited_by_count":44,"area":null},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39,"area":null},{"id":"2201.12465","title":"Flashlight: Enabling Innovation in Tools for Machine Learning","created":"2022-01-29","cited_by_count":25,"area":null},{"id":"2111.00161","title":"Pseudo-Labeling for Massively Multilingual Speech Recognition","created":"2021-10-30","cited_by_count":24,"area":null},{"id":"2207.10643","title":"STOP: A dataset for Spoken Task Oriented Semantic Parsing","created":"2022-06-29","cited_by_count":22,"area":null},{"id":"2403.07937","title":"Speech Robust Bench: A Robustness Benchmark For Speech Recognition","created":"2024-03-08","cited_by_count":21,"area":null},{"id":"2203.14222","title":"Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition","created":"2022-03-27","cited_by_count":19,"area":null},{"id":"2210.13352","title":"ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition","created":"2022-10-24","cited_by_count":18,"area":null},{"id":"2111.05948","title":"Scaling ASR Improves Zero and Few Shot Learning","created":"2021-11-10","cited_by_count":16,"area":null},{"id":"2110.08583","title":"ASR4REAL: An extended benchmark for speech models","created":"2021-10-16","cited_by_count":14,"area":null},{"id":"2310.11532","title":"Multi-stage Large Language Model Correction for Speech Recognition","created":"2023-10-17","cited_by_count":13,"area":null},{"id":"2104.01604","title":"Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers","created":"2021-04-04","cited_by_count":11,"area":null},{"id":"2506.17525","title":"Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning","created":"2025-06-21","cited_by_count":11,"area":null},{"id":"2201.12208","title":"Star Temporal Classification: Sequence Classification with Partially Labeled Data","created":"2022-01-28","cited_by_count":10,"area":null},{"id":"2206.09783","title":"Boosting Cross-Domain Speech Recognition with Self-Supervision","created":"2022-06-20","cited_by_count":10,"area":null},{"id":"2301.00304","title":"Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek","created":"2022-12-31","cited_by_count":7,"area":null},{"id":"2211.06007","title":"Continuous Soft Pseudo-Labeling in ASR","created":"2022-11-11","cited_by_count":6,"area":"distill"},{"id":"2303.07924","title":"Improving Accented Speech Recognition with Multi-Domain Training","created":"2023-03-14","cited_by_count":6,"area":null},{"id":"2409.16954","title":"Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2306.00410","title":"Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2309.17395","title":"AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition","created":"2023-09-29","cited_by_count":5,"area":null},{"id":"2309.10930","title":"Test-Time Training for Speech","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2402.04805","title":"Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training","created":"2024-02-07","cited_by_count":4,"area":"distill"},{"id":"2508.20869","title":"OLMoASR: Open Models and Data for Training Robust Speech Recognition Models","created":"2025-08-28","cited_by_count":4,"area":null},{"id":"2601.13319","title":"Arab Voices: Mapping Standard and Dialectal Arabic Speech Technology","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2112.12572","title":"Are E2E ASR models ready for an industrial usage?","created":"2021-12-09","cited_by_count":3,"area":null},{"id":"2202.12719","title":"Ask2Mask: Guided Data Selection for Masked Speech Modeling","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2207.14418","title":"Domain Specific Wav2vec 2.0 Fine-tuning For The SE&R 2022 Challenge","created":"2022-07-29","cited_by_count":3,"area":null},{"id":"2306.03773","title":"Some voices are too common: Building fair speech recognition systems using the Common Voice dataset","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2310.15672","title":"How Much Context Does My Attention-Based ASR System Need?","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2407.07566","title":"HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing","created":"2024-07-10","cited_by_count":3,"area":null},{"id":"2511.16544","title":"WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2110.05994","title":"Word Order Does Not Matter For Speech Recognition","created":"2021-10-12","cited_by_count":2,"area":null},{"id":"2110.15704","title":"Influence of ASR and Language Model on Alzheimer's Disease Detection","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2111.11170","title":"Human-Machine Interaction Speech Corpus from the ROBIN project","created":"2021-11-22","cited_by_count":2,"area":null},{"id":"2502.12408","title":"On the Robust Approximation of ASR Metrics","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2504.12254","title":"Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning","created":"2025-04-16","cited_by_count":2,"area":null},{"id":"2109.01164","title":"Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets Development","created":"2021-09-01","cited_by_count":1,"area":null},{"id":"2110.07055","title":"Continual learning using lattice-free MMI for speech recognition","created":"2021-10-13","cited_by_count":1,"area":null},{"id":"2204.05617","title":"ASR in German: A Detailed Error Analysis","created":"2022-04-12","cited_by_count":1,"area":null},{"id":"2211.17107","title":"Handling and extracting key entities from customer conversations using Speech recognition and Named Entity recognition","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2212.12048","title":"Pushing the performances of ASR models on English and Spanish accents","created":"2022-12-22","cited_by_count":1,"area":null},{"id":"2303.00510","title":"A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2311.16595","title":"D4AM: A General Denoising Framework for Downstream Acoustic Models","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2403.19822","title":"Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2509.25878","title":"ASR Under Noise: Exploring Robustness for Sundanese and Javanese","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2105.09742","title":"Robustness of end-to-end Automatic Speech Recognition Models -- A Case Study using Mozilla DeepSpeech","created":"2021-05-08","cited_by_count":0,"area":null},{"id":"2203.03583","title":"Korean Tokenization for Beam Search Rescoring in Speech Recognition","created":"2022-02-22","cited_by_count":0,"area":null},{"id":"2203.16601","title":"Is Word Error Rate a good evaluation metric for Speech Recognition in Indic Languages?","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2210.12921","title":"Investigating self-supervised, weakly supervised and fully supervised training approaches for multi-domain automatic speech recognition: a study on Bangladeshi Bangla","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2302.13222","title":"Speech Corpora Divergence Based Unsupervised Data Selection for ASR","created":"2023-02-26","cited_by_count":0,"area":null},{"id":"2404.05071","title":"Test-Time Training for Depression Detection","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2406.12937","title":"Self-Train Before You Transcribe","created":"2024-06-17","cited_by_count":0,"area":"synth"},{"id":"2409.16399","title":"Revisiting Acoustic Features for Robust ASR","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2507.09282","title":"ClaritySpeech: Dementia Obfuscation in Speech","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2603.08249","title":"Bootstrapping Audiovisual Speech Recognition in Zero-AV-Resource Scenarios","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.19151","title":"Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2607.26410","title":"Voice Memory for Agentic Speech Recognition","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2608.19936","title":"Towards Quantifying Benchmark Optimization in ASR Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.14542","title":"Neyshekar: An Open Persian Read-Speech Corpus for Automatic Speech Recognition","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}