{"total":28,"rows":[{"id":"2502.12414","title":"Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2505.12969","title":"Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down","created":"2025-05-19","cited_by_count":12,"area":null},{"id":"2510.16567","title":"Hallucination Benchmark for Speech Foundation Models","created":"2025-10-18","cited_by_count":8,"area":null},{"id":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2512.02201","title":"Swivuriso: The South African Next Voices Multilingual Speech Dataset","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2603.06193","title":"Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2503.09905","title":"Quantization for OpenAI's Whisper Models: A Comparative Analysis","created":"2025-03-12","cited_by_count":2,"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":"2508.19721","title":"CAM\\~OES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2604.08591","title":"From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2604.22631","title":"Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2508.17494","title":"Improving French Synthetic Speech Quality via SSML Prosody Control","created":"2025-08-24","cited_by_count":1,"area":null},{"id":"2603.05354","title":"Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2606.02375","title":"WAXAL-NET: Finetuned Edge ASR Across 19 African Languages","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.23060","title":"From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2607.05365","title":"SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2508.08684","title":"Out of the Box, into the Clinic? Evaluating State-of-the-Art ASR for Clinical Applications for Older Adults","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2601.11262","title":"Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.04809","title":"WhisperAlign: Word-Boundary-Aware ASR and WhisperX-Anchored Pyannote Diarization for Long-Form Bengali Speech","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.15326","title":"Tagarela - A Portuguese speech dataset from podcasts","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.25750","title":"Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2606.23048","title":"HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.22108","title":"Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.27783","title":"SURE-Voice: A Front-End Baseline for Speech-Evidence Filtering in Speech LLMs","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.04561","title":"Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection","created":"2026-09-03","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":"2609.27195","title":"Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.32560","title":"How to Reduce Whisper Hallucination","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}