Everyone deserves their voice to be heard: Analyzing Predictive Gender Bias in ASR Models Applied to Dutch Speech Data

Rik Raes, Saskia Lensink, Mykola Pechenizkiy

Recent research has shown that state-of-the-art (SotA) Automatic Speech Recognition (ASR) systems, such as Whisper, often exhibit predictive biases that disproportionately affect v…