Mar 12, 2019 / PRNewswire
Company to create an artificial intelligence (AI) system-on-chip (SoC) for always-on voice control applications
IRVINE, Calif., March 12, 2019 /PRNewswire/ — Southern California based AONdevices, led by voice and audio chip expert Mouna Elkhatib, has developed a neural network technology that can reliably recognize human speech and audio commands in very noisy environments. The technology can be implemented in a small footprint SoC for always-on battery powered applications such as smartphones and wireless headsets. The company is planning to build specialized deep learning chips for voice and audio processing and expand the framework to other applications in adjacent markets.
AON’s algorithms are based on the latest innovations in the quickly-evolving deep learning technology field, resulting in performance that as of now has not been achieved in standalone ultra-low power ASIC implementations.