Speech Robust Bench: A Robustness Benchmark For Speech Recognition

arXiv:2403.07937v1 Announce Type: cross
Abstract: As Automatic Speech Recognition (ASR) models become ever more pervasive, it is important to ensure that they make reliable predictions under corruptions present in the physical and digital world. We propose Speech Robust Bench (SRB), a comprehensive benchmark for evaluating the robustness of ASR models to diverse corruptions. SRB is composed of 69 input perturbations which are intended to simulate various corruptions that ASR models may encounter in the physical and digital world. We use …

abstract arxiv asr automatic speech recognition become benchmark cs.cl cs.lg cs.sd digital digital world eess.as predictions recognition robust robustness speech speech recognition type world