Voice user interface (VUI) is the most straightforward and intuitive human-machine interface for the future AIoT era. HAND's smart acoustic sensor is based on unique flexible piezoelectric materials and device structure, which mimics a human cochlea organ, basilar membrane (BM).
Our group has developed the multi-channel acoustic sensor showing highly sensitive recognition of human voice frequency band over 0.1 ~ 8 kHz. In particular, our miniaturized smart acoustic sensor has up to 28 times more sensitivity compared to the conventional microphone even at 1 cm scale, enabling voice recognition from a far distance. In a speaker recognition test, our voice sensor exhibited 96% accuracy rate with 62% reduction in error rate compared to commercial microphone under the noisy conditions. Furthermore, the voice signals of our acoustic sensor showed 40% improvement in the objective speech quality. Our multi-channel acoustic sensor can be applicable in the field of low power VR, AI secretary, smart home appliances, connected autonomous car, biometric authentication, and etc.
[Related References]
"Flexible Inorganic Piezoelectric Acoustic Nanosensor for Biomimetic Artificial Hair Cell" Adv. Func. Mater., 24, 6914, 2014
"Basilar Membrane-Inspired Self-Powered Acoustic Sensor Enabled by Highly Sensitive Multi Tunable Frequency Band", Nano Energy, 53, 198, 2018
"Machine Learning-based Self-powered Acoustic Sensor for Speaker Recognition", Nano Energy, 53, 658, 2018
"Biomimetic and flexible piezoelectric mobile acoustic sensors with multiresonant ultrathin structures for machine learning biometrics", Sci. Adv., 7, eabe5683, 2021
"Deep learning-based noise robust flexible piezoelectric acoustic sensors for speech processing", Nano Energy, 101, 107610, 2022
Voice user interface (VUI) is the most straightforward and intuitive human-machine interface for the future AIoT era. HAND's smart acoustic sensor is based on unique flexible piezoelectric materials and device structure, which mimics a human cochlea organ, basilar membrane (BM).
Our group has developed the multi-channel acoustic sensor showing highly sensitive recognition of human voice frequency band over 0.1 ~ 8 kHz. In particular, our miniaturized smart acoustic sensor has up to 28 times more sensitivity compared to the conventional microphone even at 1 cm scale, enabling voice recognition from a far distance. In a speaker recognition test, our voice sensor exhibited 96% accuracy rate with 62% reduction in error rate compared to commercial microphone under the noisy conditions. Furthermore, the voice signals of our acoustic sensor showed 40% improvement in the objective speech quality. Our multi-channel acoustic sensor can be applicable in the field of low power VR, AI secretary, smart home appliances, connected autonomous car, biometric authentication, and etc.
[Related References]
"Flexible Inorganic Piezoelectric Acoustic Nanosensor for Biomimetic Artificial Hair Cell" Adv. Func. Mater., 24, 6914, 2014
"Basilar Membrane-Inspired Self-Powered Acoustic Sensor Enabled by Highly Sensitive Multi Tunable Frequency Band", Nano Energy, 53, 198, 2018
"Machine Learning-based Self-powered Acoustic Sensor for Speaker Recognition", Nano Energy, 53, 658, 2018
"Biomimetic and flexible piezoelectric mobile acoustic sensors with multiresonant ultrathin structures for machine learning biometrics", Sci. Adv., 7, eabe5683, 2021
"Deep learning-based noise robust flexible piezoelectric acoustic sensors for speech processing", Nano Energy, 101, 107610, 2022