KAIST Vision Hall
Important On-campus Websites
Personal Information Policy
Main Campus (Daejeon)
Seoul Campus (Seoul)
Munji Campus (Daejeon)
Dogok Campus (Seoul)
How to get to KAIST
Giving to KAIST
Excellence in KAIST
Use of Gift
Make a Gift
College of Natural Sciences
College of Life Science and Bio Engineering
College of Engineering
College of Liberal Arts and Convergence Science
College of Business
General Studies Requirements
Education Support Program
Int'l Exchange Programs
International Scholar and Student Service Team
Center for Excellence in Learning and Teaching
Research Areas and Main Research Programs
Person in Charge by Research Area
Common Utilized Equipment
Office of Univ. Industry Coop.
World Economic Forum
KAIST Annual R&D Report
Student Health Insurance Association
Cultural Event Info.
Satisfaction survey of food&beverage Enterprise inside Campus
Day Care Center
Student Clubs and Activities
Undergraduate Student Clubs
Graduate Student Clubs
Center For Ethics And Human Rights
Intl’ Student Identity Card (ISIC)
KAIST in Media
International Scholar and Student Services
Flexible Piezoelectric Acoustic Sensors for Speaker Recognition
A KAIST research team led by Professor Keon Jae Lee from the Department of Material Science and Engineering has developed a machine learning-based acoustic sensor for speaker recognition.
Acoustic sensors were spotlighted as one of the most intuitive bilateral communication devices between humans and machines. However, conventional acoustic sensors use a condenser-type device for measuring capacitance between two conducting layers, resulting in low sensitivity, short recognition distance, and low speaker recognition rates.
The team fabricated a flexible piezoelectric membrane by mimicking the basilar membrane in the human cochlear. Resonant frequencies vibrate corresponding regions of the trapezoidal piezoelectric membrane, which converts voice to electrical signal with a highly sensitive self-powered acoustic sensor.
This multi-channel piezoelectric acoustic sensor exhibits sensitivity more than two times higher and allows for more abundant voice information compared to conventional acoustic sensors, which can detect minute sounds from farther distances. In addition, the acoustic sensor can achieve a 97.5% speaker recognition rate using a machine learning algorithm, reducing by 75% error rate than the reference microphone.
AI speaker recognition is the next big thing for future individual customized services. However, conventional technology attempts to improve recognition rates by using software upgrades, resulting in limited speaker recognition rates. The team enhanced the speaker recognition system by replacing the existing hardware with an innovative flexible piezoelectric acoustic sensor. Further software improvement of the piezoelectric acoustic sensor will significantly increase the speaker and voice recognition rate in diverse environments.
Professor Lee said, “Highly sensitive self-powered acoustic sensors for speaker recognition can be used for personalized voice services such as smart home appliances, AI secretaries, always-on IoT, biometric authentication, and FinTech.”
These research “Basilar Membrane-Inspired Self-Powered Acoustic Sensor” and “Machine Learning-based Acoustic Sensor for Speaker Recognition” were published in the September 2018 issue of Nano Energy.
Firgure 1: A flexible piezoelectric acoustic sensor mimicking the human cochlear.
Figure 2: Speaker recognition with a machine learning algorithm.