While most mobile phones incorporate a voice-recognition feature, the usefulness and accuracy of voice recognition can be adversely affected by the ambient noise environment. Being that a mobile phone is essentially a microphone, it is all too easy the voice recognition to inadvertently activate due to ambient noise or other extraneous conversations.
Two scientists from Pohang University of Science and Technology (POSTECH) in Pohang, South Korea have developed a flexible and wearable vibration responsive sensor. The sensor, developed by Professor Kilwon Cho of Chemical Engineering and Professor Yoonyoung Chung of Electronic and Electric Engineering, can precisely recognize voice through vibration of the neck’s skin and is not affected by ambient noise or the volume of sound.
Conventional vibration sensors, which recognize voice through air vibration, lose their sensitivity due to mechanical resonance and damping effects. Consequently, ambient sound or obstacles such as a mouth mask can affect voice recognition accuracy and cannot be used for security authentication.
The researchers found that voice pressure is proportional to the acceleration of neck skin vibration at various sound pressure levels from 40 to 70 dBSPL (a measurement of sound pressure). They developed a vibration sensor, comprising an ultrathin polymer film and a diaphragm with tiny holes, that can sense voices quantitatively by measuring the acceleration of skin vibration.
The researchers also demonstrated that the device can accurately recognize voice without vibrational distortion, even in noisy environments and at a very low voice volume with a mouth mask worn. They believe this research can be further extended to various voice-recognition applications such as an electronic skin, human-machine interface, or wearable vocal healthcare monitoring device.
“This research is very meaningful in a way that it developed a new voice-recognition system which can quantitatively sense and analyze voice and is not affected by the surroundings “ says Professor Cho in a statement. “It took a step forward from the conventional voice-recognition system that could only recognize voice qualitatively.”
This research was supported by the Center for Advanced Soft Electronics under the Global Frontier Research Program of The Ministry of Science and ICT, Korea. Additional results of the study appear on the website of Nature Communications.