Pukyong National University Professor Develops Noise Cancellation Tech with Meta for AI Glasses

At a glance

A research team led by Professor Lee Dong-heon at Pukyong National University developed technology with Meta to reduce surrounding noise and sharpen voices on small devices such as AI glasses. Using sound from four microphones, it reached audio quality close to that of more than 16 microphones.

Key points

1. 1

   It fills in sound information for other positions using the sound received by four microphones.

2. 2

   It cuts the computing needed so it can run in real time on small devices.

3. 3

   Its performance was also checked in settings where the speaker is moving.

4. 4

   The research paper was accepted to the AI conference NeurIPS 2026.

Why it matters

It is expected to improve voice recognition and call quality in AI glasses and hearing aids.

Also reported by

• 아시아경제국립부경대 이동헌 교수·Meta, AI 글래스용 노이즈 캔슬링 기술 개발
• CNB뉴스국립부경대 이동헌 교수, Meta와 AI 글래스용 노이즈 캔슬링 기술 개발