{"total":20,"rows":[{"id":"2505.24347","title":"Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2511.04139","title":"CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2505.21230","title":"PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systems","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2603.22915","title":"When AVSR Meets Video Conferencing: Dataset, Degradation, and the Hidden Mechanism Behind Performance Collapse","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2506.11064","title":"PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2508.03542","title":"Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.15095","title":"Listening, Imagining & Refining: A Heuristic Optimized ASR Correction Framework with LLMs","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2601.15339","title":"Lost in Transcription: How Speech-to-Text Errors Derail Code Understanding","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2506.10779","title":"Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2508.08027","title":"Bridging ASR and LLMs for Dysarthric Speech Recognition: Benchmarking Self-Supervised and Generative Approaches","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.14263","title":"Context-Enhanced Granular Edit Representation for Efficient and Accurate ASR Post-editing","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2509.23630","title":"Game-Oriented ASR Error Correction via RAG-Enhanced LLM","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2512.02027","title":"On the Difficulty of Token-Level Modeling of Dysfluency and Fluency Shaping Artifacts","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.19161","title":"From Speech to Subtitles: Evaluating ASR Models in Subtitling Italian Television Programs","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2512.20032","title":"VALLR-Pin: Uncertainty-Factorized Visual Speech Recognition for Mandarin with Pinyin Guidance","created":"2025-12-23","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":"2607.08208","title":"Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.09889","title":"Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.20504","title":"Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.15056","title":"Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}