Artificial intelligence may be making small and steady advances in general-purpose situations like digital assistants. But it’s the more subtle AI accessibility features that have a more substantial impact today, especially for users with disabilities. For instance, an upcoming feature for Office apps like Microsoft Word and PowerPoint will automatically suggest image and slide deck captions, called alt-text, using AI algorithms. That way, when those files are presented to blind users, computer tools designed to translate the information onscreen into audio have text descriptions to work with.

Improvement for Blind Users from Microsoft Ai

Microsoft is accomplishing this feat with its Computer Vision Cognitive Service, which uses neural networks trained with deep learning techniques to better understand and describe the contents of images. “We will offer you automatic suggestions for alt-text when you insert a photographic image that can be recognized with high confidence,” writes the Office 365 team in a blog post. “Through machine learning, this service will keep improving as more people use it, saving you significant time to make media-rich presentations accessible.” Facebook too announced a similar feature for photo captions back in April, and much of the tech industry is using these AI techniques to both improve accessibility and better parse images and videos for valuable data.

The feature will be available in Office and PowerPoint on PC starting next year for Office 365 subscribers. Microsoft also says it will be releasing accessible templates that for Office apps that are “structured to ensure ease of navigation with a screen reader and keyboard and use fonts and colors that are easy to read with low vision or color blindness.” For those who choose to customize their documents or slide decks, Microsoft says it has released an accessibility checker for Office PC apps that will review the file and fix any issues that make it difficult for users with disabilities to access the information. New images are added.

Comments

comments