Trouble in Your Tank: Implementing Direct Metallization in Advanced Substrate Packaging
It’s Only Common Sense: Storytelling That Sells—Stop Pitching, Start Painting Pictures
The Right Approach: Get Ready for ISO 9001 Version 6
Flexible Piezoelectric Acoustic Sensors for Speaker Recognition
October 5, 2018 | KAISTEstimated reading time: 1 minute
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.
Figure 1: A flexible piezoelectric acoustic sensor mimicking the human cochlear.
Figure 2: Speaker recognition with a machine learning algorithm.
Share on:
Testimonial
"We’re proud to call I-Connect007 a trusted partner. Their innovative approach and industry insight made our podcast collaboration a success by connecting us with the right audience and delivering real results."
Julia McCaffrey - NCAB GroupSuggested Items
Secure Semiconductor Manufacturing Acquires Full SMT Line from Manncorp
09/11/2025 | ManncorpSecure Semiconductor Manufacturing, LLC (SSM), an American-owned company dedicated to producing secure printed wiring boards and advanced assembly solutions in the MidWest USA, today announced the acquisition of a complete surface mount technology (SMT) line from Manncorp.
Driving Innovation: Depth Routing Processes—Achieving Unparalleled Precision in Complex PCBs
09/08/2025 | Kurt Palmer -- Column: Driving InnovationIn PCB manufacturing, the demand for increasingly complex and miniaturized designs continually pushes the boundaries of traditional fabrication methods, including depth routing. Success in these applications demands not only on robust machinery but also sophisticated control functions. PCB manufacturers rely on advanced machine features and process methodologies to meet their precise depth routing goals. Here, I’ll explore some crucial functions that empower manufacturers to master complex depth routing challenges.
MS2 Technologies, LLC/P. Kay Focuses on Central America with First Installation in Honduras
08/24/2025 | P. Kay Metal, Inc.This year MS2 Technologies has turned their focused to the growing electronics market in Central America. With that focus came the adaptation of MS2 and the Akila System from a Honduras-based corporation with manufacturing plants in both Honduras and Mexico.
SEL: Revolutionizing PCB Production Through MES, Partnerships, and Vision
08/21/2025 | Barry Matties, I-Connect007Two years ago, we visited Schweitzer Engineering Laboratories (SEL) to better understand its new captive greenfield PCB facility. We recently returned, this time to discuss how this bold vision has transformed the industry. Barry Matties met with John Hendrickson, engineering director, and Jessi Hall, vice president of vertical integration, to discuss the transformative capabilities of Factory Core, SEL’s custom manufacturing execution system (MES), which allows for real-time monitoring of workflow and machine performance, and has led to impressive improvements in quality and cost efficiency.
Smart Automation: Pick-and-place Machines—What Matters in 2025
08/12/2025 | Josh Casper -- Column: Smart AutomationWhen people talk about placement technology, they often zero in on speed: How fast can a machine place components? What's the quoted components per hour (CPH)? How many nozzles are on the head? While these metrics matter, on most production floors, the fastest machine on paper isn’t always the most productive.
Copyright © I-Connect007 | IPC Publishing Group Inc. All rights reserved.
Log in