Microsoft filed 2 patents, all in Audio.
The filings cover AI-powered real-time Audio transformation technology that allows users to replace, remove, or enhance specific sounds during gameplay using generative AI. This Audio modification system targets players who experience adverse reactions to certain game sounds, such as those with PTSD, misophonia, or phonophobia, enabling them to customize their Audio experience by filtering or altering triggers like gunshots and explosions.
Microsoft's 2 Audio patents both tackle the same challenge of helping gamers manage triggering sounds during gameplay. The technology uses generative AI to identify and transform specific sound classes in real-time Audio streams, allowing players to replace, remove, or modify sounds like gunshots or explosions based on personal sensitivities. The system goes beyond simple volume controls by semantically understanding Audio content and applying transformations without requiring developers to build support into individual games. One filing emphasizes the ability to stack multiple AI models in a processing pipeline and train personalized models using a user's own Audio samples, while the other highlights a feedback loop that refines the model when it misses or incorrectly processes sounds, plus the ability to sync trained models across devices through a global user account.
All data sourced from USPTO patent filings. Google Patents may take several weeks to index recent publications. If a link is unavailable, search for the patent number at USPTO Patent Public Search.