Explainable AI for Audio via Virtual Inspection Layers
Johanna Vielhaben
Sebastian Lapuschkin
Grégoire Montavon
Wojciech Samek
The field of eXplainable Artificial Intelligence (XAI) has made significant advancements in recent years. However, most progress has focused on computer vision and natural language processing. There has been limited research on XAI specifically for audio or other time series data, where the input itself is often hard to interpret. In this study, we introduce a virtual inspection layer that transforms time series data into an interpretable representation and enables the use of local XAI methods to attribute relevance to this representation
Workshop Recording: https://nips.cc/virtual/2023/79736
