{"total":28,"rows":[{"id":"2309.07081","title":"Can Whisper perform speech-based in-context learning?","created":"2023-09-13","cited_by_count":35,"area":null},{"id":"2410.04527","title":"Casablanca: Data and Models for Multidialectal Arabic Speech Recognition","created":"2024-10-06","cited_by_count":20,"area":null},{"id":"2407.06800","title":"Learn and Don't Forget: Adding a New Language to ASR Foundation Models","created":"2024-07-09","cited_by_count":16,"area":null},{"id":"2406.02925","title":"Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2410.16726","title":"Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap","created":"2024-10-22","cited_by_count":12,"area":null},{"id":"2410.20817","title":"The Zeno's Paradox of `Low-Resource' Languages","created":"2024-10-28","cited_by_count":12,"area":null},{"id":"2402.02302","title":"Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens","created":"2024-02-03","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":"2406.10284","title":"Improving child speech recognition with augmented child-like speech","created":"2024-06-12","cited_by_count":7,"area":null},{"id":"2402.04222","title":"What is \"Typological Diversity\" in NLP?","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2410.00511","title":"Pre-training with Synthetic Patterns for Audio","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2602.04776","title":"Speaker-Aware Simulation Improves Conversational Speech Recognition","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2404.02408","title":"CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing Models","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2406.13502","title":"ManWav: The First Manchu ASR Model","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2505.24200","title":"Improving Multilingual Speech Models on ML-SUPERB 2.0: Fine-tuning with Data Augmentation and LID-Aware CTC","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2507.21331","title":"A Deep Learning Automatic Speech Recognition Model for Shona Language","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2601.06802","title":"Doing More with Less: Data Augmentation for Sudanese Dialect Automatic Speech Recognition","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2404.17983","title":"TI-ASU: Toward Robust Automatic Speech Understanding through Text-to-speech Imputation Against Missing Speech Modality","created":"2024-04-27","cited_by_count":0,"area":null},{"id":"2409.08872","title":"Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2501.14788","title":"Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages","created":"2025-01-08","cited_by_count":0,"area":null},{"id":"2507.16843","title":"Weak Supervision Techniques towards Enhanced ASR Models in Industry-level CRM Systems","created":"2025-07-20","cited_by_count":0,"area":null},{"id":"2604.24770","title":"Elderly-Contextual Data Augmentation via Speech Synthesis for Elderly ASR","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.19711","title":"Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West Frisian","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2607.22304","title":"Synthetic Speech, Real Signal: Paralinguistic Preservation and Cross-Lingual Augmentation via Voice Cloning","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.26697","title":"Phoneme-guided TTS augmentation for ASR: A unified pipeline and multilingual evaluation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.18194","title":"T-SANDHI: Tone Sandhi-aware Adaptive Network with Decoupled Hybrid Injection for Low-resource Taiwanese Hokkien Speech Recognition","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.13807","title":"Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASR","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}