FrontierAugust 28, 2026via GeekWire
UW AI researcher wins top Marconi award and aims to put ‘superhuman hearing’ in billions of devices
Why it matters
Efficient on-device AI for audio is a frontier capability problem: extracting speech in noise on low-power hardware challenges model design, optimization, and inference. This award signals a solved pattern that practitioners building hearables and edge audio products need to track.
Key signals
- Malek Itani (UW Ph.D.) won Marconi Prize for on-device audio AI
- Co-founded Hearvana for real-time sound enhancement
- Capability: target speech extraction, 'sound bubbles,' semantic hearing on low-power earbuds/hearing aids
- Real-time inference on edge hardware — no cloud dependency
- Target market: billions of hearable devices
- Malek Itani (UW Ph.D. student, Hearvana co-founder) wins Marconi Award
- On-device AI algorithms enable real-time target speech extraction
- 'Sound bubbles' and semantic hearing capabilities
- Deployed on low-power hearables (earbuds, hearing aids)
- No cloud dependency — runs locally
- Implication: scale to billions of devices
The hook
UW researcher's on-device 'superhuman hearing' AI wins Marconi Prize — real-time speech extraction on earbuds without cloud.
Ph.D. student Malek Itani, who co-founded the AI-powered sound enhancement startup Hearvana, was recognized for developing on-device AI algorithms that enable real-time target speech extraction, "sound bubbles," and semantic hearing on low-power hearables like earbuds and hearing aids.