Flexible piezoelectric acoustic sensors for speaker recognition

October 5, 2018, The Korea Advanced Institute of Science and Technology (KAIST)
Flexible piezoelectric acoustic sensors for speaker recognition
A flexible piezoelectric acoustic sensor mimicking the human cochlear. Credit: KAIST

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 were spotlighted as among 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 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 percent recognition rate using a machine learning algorithm, reducing by 75 percent 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 can be used for personalized services such as smart home appliances, AI secretaries, always-on IoT, biometric authentication, and FinTech."

Explore further: A new triboelectric auditory sensor for social robotics and hearing aids

More information: Jae Hyun Han et al, Basilar membrane-inspired self-powered acoustic sensor enabled by highly sensitive multi tunable frequency band, Nano Energy (2018). DOI: 10.1016/j.nanoen.2018.08.053

Related Stories

Voice impersonators can fool speaker recognition systems

November 15, 2017

Skilful voice impersonators are able to fool state-of-the-art speaker recognition systems, as these systems generally aren't efficient in recognising voice modifications, according to new research from the University of Eastern ...

Pencil test for pipeline cracks

June 8, 2016

It is impossible to see when the "lead" in a pencil cracks within the pencil, but an acoustic sensor can "hear" the change in the way the pencil vibrates. Now, researchers in China have reported in the International Journal ...

Marine exploration sensing with light and sound

March 13, 2018

Oceanic sensor networks that collect and transmit high-quality, real-time data could transform the understanding of marine ecology, improve pollution and disaster management, and inform multiple industries that draw on ocean ...

Phone snooping via gyroscope to be detailed at Usenix

August 15, 2014

Put aside fears of phone microphones and cameras doing eavesdropping mischief for a moment, because there is another sensor that has been flagged. Researchers from Stanford and defense research group at Rafael will present ...

Recommended for you


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.