"This is just one problem Norwegian startup Hance is solving with an impressively small and fast bit of audio processing software that's already attracted customers like Intel and Riedel Communications, the official radio supplier to F1. Hance is one of the 200 startups selected to show off its technology at TechCrunch Disrupt 2025, which runs October 27 through 29 at Moscone Center in San Francisco."
"Since then, they've been able to shrink the Hance processing models to just 242 kB, meaning they can run on device instead of in the cloud, saving time and energy. Hance says these models can separate sounds, remove noise, echo, and reverb, and enhance speech clarity with just 10 milliseconds of latency. While other companies offer similar audio processing software, Hance's tiny, energy-efficient models can process audio on devices of all sizes in real-time."
Hance is a Norwegian audio startup of about ten employees built by industry veterans including Stian Aagedal and Peder J f8rgensen. The team trained custom models on high-quality Soundly recordings spanning motorsport roars to volcanic rumbles. The Hance processing models have been compressed to roughly 242 kB so they can run on-device rather than in the cloud, reducing latency and energy use. The models can separate sounds, remove noise, echo, and reverb, and improve speech clarity with approximately 10 milliseconds of latency. Customers include Intel and Riedel Communications, and the technology suits real-time, resource-constrained applications.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]