Femtosense designs AI processors that exploit sparsity in neural networks to cut power and memory use. Its SPU-001 chip runs speech enhancement, noise suppression and keyword spotting in hearing aids, earbuds and voice-controlled appliances while consuming well under a milliwatt. The company provides a compiler that prunes and quantizes models from PyTorch for its architecture, and it works with consumer electronics and medical device manufacturers.
Focus: sparse ai processors, audio ai.
Tags: sparse ai · speech enhancement · hearing aids · voice · tinyml
More edge ai companies
Alif Semiconductor
Ensemble and Balletto microcontrollers with Arm Ethos NPUs for battery-powered AI
Ambarella
Computer vision SoCs with on-chip neural network engines for cameras, robots and vehicles
Aspinity
Analog machine learning chips that classify sensor data before it is digitized