Edge Sound raises $2 million for physical AI audio

Edge Sound Research's approach to machine perception centres on connecting audio with tracking and visual data to determine which sound belongs to which object. The company first tackled this problem in sports, where overlapping sounds from fans, speakers and the game itself complicate isolating a simple dribble. Its Virtual Sound Engine, which automatically captures and isolates sound from complex environments, is already deployed commercially across the industry, with customers and partners including Shure Inc., the National Basketball Association, Fox Sports Media Group and the United States Tennis Association Inc.

The new funding is intended to complete integration with existing enterprise customers and make the platform's components transferable across industries ahead of a Series A. Edge Sound's digital twin software and AI models aim for hardware independence, so the audio infrastructure can work alongside microphones and cameras that customers already use. The company sees potential beyond media in autonomous vehicles, which could be given digital ears to hear a siren approaching from a blind corner even when cameras cannot see it.