Voice recognition (VR) is the most straight forward and intuitive user-interface for the future IoT era. FAND's smart acoustic sensor is based on unique flexible piezoelectric materials and device structure , which mimics a human cochlear organ.
We have developed multi-channel acoustic sensor capable of highly sensitive recognition of human voice frequency band, 200 ~ 4kHz. In particular, our smart acoustic sensor has 4 to 8 times more sensitivity compare to the conventional microphone, that enables voice recognition from a distance. In a speaker recognition rate test, FAND's acoustic sensor was 97.5% and a reference microphone used in commercial cellular phone was 90%, which was 75% reduction in error rate compared to reference microphone under the same conditions. FAND group's multi-channel acoustic sensor can be applicable in the field of low power VR, AI, smart home applicances, connected car, voice security, and etc.