← Search

Marcin Witkowski

2 accepted papers

2025

Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio

ICASSP 2025accepted

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 by non-speech audio segments present during inference. By inducting hallucinations with various types of sounds, we sho…

Cited by 0SourceScholar
2022

Convolutional Weighted Minimum Mean Square Error Filter for Joint Source Separation and Dereverberation

ICASSP 2022accepted

Practical scenarios with multiple simultaneously active speakers recorded using one or more microphones in reverberant rooms pose a challenging problem when the extraction of the desired speaker signal is sought for. The majority of techniques found in the literature facilitate either source separat…

Cited by 6SourceScholar