{"total":23,"rows":[{"id":"2402.08021","title":"Careless Whisper: Speech-to-Text Hallucination Harms","created":"2024-02-12","cited_by_count":53,"area":null},{"id":"2501.11378","title":"Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio","created":"2025-01-20","cited_by_count":31,"area":null},{"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":"2409.06109","title":"Estimating the Completeness of Discrete Speech Units","created":"2024-09-09","cited_by_count":9,"area":null},{"id":"2510.16567","title":"Hallucination Benchmark for Speech Foundation Models","created":"2025-10-18","cited_by_count":8,"area":null},{"id":"2604.19300","title":"HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models","created":"2026-04-21","cited_by_count":8,"area":null},{"id":"2604.21276","title":"Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2506.08846","title":"Addressing Pitfalls in Auditing Practices of Automatic Speech Recognition Technologies: A Case Study of People with Aphasia","created":"2025-06-10","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":"2512.17915","title":"Supplementary Resources and Analysis for Automatic Speech Recognition Systems Trained on the Loquacious Dataset","created":"2025-11-27","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":"2608.27135","title":"Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2407.04280","title":"LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2407.20556","title":"Survey of Design Paradigms for Social Robots","created":"2024-07-30","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":"2608.24707","title":"Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2405.03484","title":"Whispy: Adapting STT Whisper Models to Real-Time Environments","created":"2024-05-06","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":"2603.20433","title":"When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removal","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.25727","title":"Back to Basics: Revisiting ASR in the Age of Voice Agents","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.19565","title":"Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps","created":"2026-04-21","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}],"next_cursor":null}