What's New in Wolfram Image & Audio?

Recent developments in artificial intelligence have given image and signal processing a gigantic boost. This year, we focus on the advancements in image segmentation, OCR and speech recognition and synthesis. We have integrated neural networks directly into the system or connected to them via services and APIs. In this talk, we introduce you to the powerful underlying neural network structures, such as U-Nets and visual transformers, and demonstrate a range of applications where these novel functions facilitate entire new workflows.

apis artificial artificial intelligence audio boost focus image intelligence networks neural networks ocr processing recognition segmentation services signal speech speech recognition synthesis talk them via wolfram