7 citations · 9 across the 4 of their papers we have counts for
4 papers
From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection
Jan Jasiński, Mateusz Barański, 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…
HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems
Mateusz Barański, Jan Jasiński, 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…
Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio
Mateusz Barański, Jan Jasiński, 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…
HeightCeleb - an enrichment of VoxCeleb dataset with speaker height information
Stanisław Kacprzak, Konrad Kowalczyk
Prediction of speaker's height is of interest for voice forensics, surveillance, and automatic speaker profiling. Until now, TIMIT has been the most popular dataset for training an…