7 citations · 9 across the 5 of their papers we have counts for
5 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…
Refining DNN-based Mask Estimation using CGMM-based EM Algorithm for Multi-channel Noise Reduction
Julitta Bartolewska, Stanisław Kacprzak, Konrad Kowalczyk
In this paper, we present a method that allows to further improve speech enhancement obtained with recently introduced Deep Neural Network (DNN) models. We propose a multi-channel…
Causal Signal-Based DCCRN with Overlapped-Frame Prediction for Online Speech Enhancement
Julitta Bartolewska, Stanisław Kacprzak, Konrad Kowalczyk
The aim of speech enhancement is to improve speech signal quality and intelligibility from a noisy microphone signal. In many applications, it is crucial to enable processing with…