What's New in Wolfram Image & Audio?

Shadi Ashnai and Markus van Almsick

Recent developments in AI give image and signal processing a major boost. We focus on advancements in image segmentation, OCR and speech recognition and synthesis. We integrated neural networks directly into the system or connected to them via services and APIs. We cover the powerful underlying neural network structures, such as U-Nets and visual transformers, and demonstrate applications where these functions facilitate new workflows.