This period includes 5 filed patent applications across 3 companies: Sony (3), Meta (1), and Silicon Audio Directional (1).
Sony's applications focus on adaptive audio systems for gaming, including a machine learning text-to-speech platform that allows phoneme-level voice pitch control for dynamic character dialogue and a voice chat system that adjusts communication between players based on their in-game relationships and locations. Meta's application describes a spatial audio system that repositions sound in real time as users move their heads in VR and AR environments. Silicon Audio Directional's application covers directional microphone technology using pressure gradient sensing, while another application details an AI system that balances in-game audio with external sound streams during gameplay.
Sony received 3 patents centered on adaptive audio for gaming environments. The first addresses text-to-speech systems by splitting pitch prediction from pitch application, allowing developers to manually adjust voice pitch at the phoneme level after an initial machine learning model generates baseline predictions. The second patent describes an AI system that monitors gameplay context to identify critical moments, like boss battles or teammate alerts, and automatically adjusts competing audio streams to prevent important sounds from being masked. The third covers voice chat processing that modifies communication quality based on in-game context, such as muffling voices of enemy players or applying distance-based effects to simulate realistic communication constraints between characters.
Meta received 1 patent for a spatial audio system designed for VR and AR applications. The technology uses two coordinated algorithms to update sound positioning as users turn their heads, combining real-time head angle tracking with adaptive filtering that prevents audio sources from drifting or creating disorientation during natural head movements.
Silicon Audio Directional received 1 patent for directional microphone hardware. The design uses multiple deformable elements connected to a shared cavity, where coupled vibration modes respond differently to uniform pressure compared to pressure gradients, enabling the system to capture sound directionally and apply beam steering through signal processing and neural network analysis.
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.