Smart Mics That Follow the Sound: On-Device AI for Clearer Audio
Ever wished your mic could zoom in on the right voice, even in a noisy room? This research shows how.
An on-device deep learning tracker works with a compact ring-shaped array of tiny MEMS microphones to steer a "listening beam" in real time—locking onto a moving target and turning down distractions.
- Finds where a sound comes from in 3D using a single camera plus stereo depth cues.
- Steers listening left-right and up-down via a concentric circular array.
- Adapts as people move, boosting signal-to-interference for clearer speech.
Why it matters: cleaner calls, smarter home assistants, better robots, and more reliable assistive tech—even with multiple talkers.
By Jorge Ortigoso-Narro, Jose A. Belloch, Adrian Amor-Martin, Sandra Roger, and Maximo Cobos. Read more: https://arxiv.org/abs/2511.19396v1
Paper: https://arxiv.org/abs/2511.19396v1
Register: https://www.AiFeta.com
audioAI beamforming computerVision edgeAI HCI robotics smarthome teleconferencing assistiveTech microphones MEMS
