2025
Unveiling Performance Bias in ASR Systems: A Study on Gender, Age, Accent, and More
Maliha Jahan, Priyam Mazumdar, Thomas Thebaud, Mark Hasegawa-Johnson, Jesús Villalba, Najim Dehak +1
ICASSP 2025accepted
With the recent advancements in speech recognition, it is crucial to ensure these systems are free from performance biases against any speaker subgroups. This study examined the performance of twenty variants of seven Automatic Speech Recognition models across four datasets in English language: L2 A…