Current automatic speech recognition (ASR) models are designed to be used across many languages and tasks without substantial changes. However, this broad language coverage hides performance gaps within languages, for example, across genders. Our …
Predictive models make mistakes and have biases. To combat both, we need to understand their predictions.Explainable AI (XAI) provides insights into models for vision, language, and tabular data. However, only a few approaches exist for speech …