3 papers
cs.SD2026
From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection
Jan JasiÅski, Mateusz BaraÅski, Julitta Bartolewska +2
Hallucinations of ASR models - fluent transcriptions with no basis in audio - degrade system performance and pose risks in downstream applications. Robust detection of such errors…
cs.SD2026
HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems
Mateusz BaraÅski, Jan JasiÅski, Julitta Bartolewska +2
End-to-end Automatic Speech Recognition (ASR) systems hallucinate on natural speech, yet existing mitigation methods are typically evaluated on non-speech or artificially corrupted…
cs.SD2025
Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio
Mateusz BaraÅski, Jan JasiÅski, Julitta Bartolewska +3
Hallucinations of deep neural models are amongst key challenges in automatic speech recognition (ASR). In this paper, we investigate hallucinations of the Whisper ASR model induced…