Mauricio Greene of Bolom demonstrates real-time Sound Classification running on the Cadence Tensilica HiFi 5 DSP at the Embedded Vision Summit. Bolom Acoustic Intelligence edge models identify hundreds of distinct sound events and soundscape scenes – such as sirens, alarms, horns, traffic and more, fully on-device and without relying on the cloud. The Tensilica HiFi 5, optimized for AI-based audio processing, provides the high-performance, low-power compute backbone needed to run Bolom audio models in real time on embedded hardware. This demonstration highlights how Bolom’s processor-agnostic software integrates natively with edge SoCs to bring machine listening to automotive, robotics, and IoT applications. Learn more at intelligence.bolom.com
