{"total":27,"rows":[{"id":"2406.10507","title":"Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models","created":"2024-06-15","cited_by_count":29,"area":null},{"id":"2409.14494","title":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments","created":"2024-09-13","cited_by_count":7,"area":null},{"id":"2501.08468","title":"Selective Attention Merging for low resource tasks: A case study of Child ASR","created":"2025-01-14","cited_by_count":6,"area":null},{"id":"2508.16576","title":"Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet","created":"2025-08-22","cited_by_count":6,"area":null},{"id":"2406.13431","title":"Children's Speech Recognition through Discrete Token Enhancement","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2509.02830","title":"SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2512.18263","title":"TICL+: A Case Study On Speech In-Context Learning for Children's Speech Recognition","created":"2025-12-20","cited_by_count":4,"area":null},{"id":"2406.17926","title":"FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data","created":"2024-06-25","cited_by_count":3,"area":null},{"id":"2410.11865","title":"Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2601.20142","title":"Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2506.02412","title":"SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2409.16135","title":"Evaluation of Speech Foundation Models for ASR on Child-Adult Conversations in Autism Diagnostic Sessions","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2506.06071","title":"CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2506.09206","title":"SimClass: A Classroom Speech Dataset Generated via Game Engine Simulation For Automatic Speech Recognition Research","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2601.12600","title":"SSVD-O: Parameter-Efficient Fine-Tuning with Structured SVD for Speech Recognition","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2606.11429","title":"Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2409.13095","title":"Examining Test-Time Adaptation for Personalized Child Speech Recognition","created":"2024-09-19","cited_by_count":0,"area":null},{"id":"2505.17088","title":"From Weak Labels to Strong Results: Utilizing 5,000 Hours of Noisy Classroom Transcripts with Minimal Accurate Data","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2510.01462","title":"RealClass: A Framework for Classroom Speech Simulation with Public Datasets and Game Engines","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2512.05994","title":"KidSpeak: A General Multi-purpose LLM for Kids' Speech Recognition and Screening","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2603.13710","title":"InterventionLens: A Multi-Agent Framework for Detecting ASD Intervention Strategies in Parent-Child Shared Reading","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.20255","title":"Abjad-Kids: An Arabic Speech Classification Dataset for Primary Education","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2607.27212","title":"Digital Harf: A Clinically Integrated Multimodal AI System for Pervasive Arabic Speech and Language Therapy","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2609.17981","title":"Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.23979","title":"AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.38106","title":"Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.08827","title":"Child ASR Adaptation with Adult Retention: An Empirical Study","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}