| 학회 |
한국재료학회 |
| 학술대회 |
2019년 가을 (10/30 ~ 11/01, 삼척 쏠비치 호텔&리조트) |
| 권호 |
25권 2호 |
| 발표분야 |
E. 환경/센서 재료 분과 |
| 제목 |
Highly-Sensitive Flexible Piezoelectric Acoustic Sensors for Speaker Recognition |
| 초록 |
Herein, we demonstrate a new concept of flexible piezoelectric acoustic sensors (f-PAS) using mechanical sequential resonance in membrane. The flexible piezoelectric film of f-PAS fabricated by sol-gel method and inorganic laser lift-off (LLO) shows high sensitivity to nanometer scale vibration and low frequency resonance in human voice frequency region. The self-powered f-PAS mimicked mechanism of the basilar membrane in the human cochlear that has multiple response to specific frequency in hair cells. The f-PAS exhibits maximum -42dB of relative sensitivity, which is four to eight times higher than the conventional condenser sensor without any amplifier. The f-PAS acquired abundant voice information from the multi-channel sound inputs and read the tiny voice characteristics due to high sensitivity. The standard records dataset (TIDIGITs) were played to excite the piezoelectric membrane of the f-PAS, which transduce the mechanical vibration to the electrical analog signal. The voltage-time data was subsequently analyzed by a Fast Fourier Transform (FFT) and a Short-Time Fourier Transform (STFT) to convert to the frequency component. The machine learning based algorithm was designed by utilizing the most highest and second highest sensitivity data among multi-channel outputs, exhibiting outstanding speaker recognition rate of 97.5% with error rate reduction of 75%, compared to that of the reference condense-type MEMS microphone. |
| 저자 |
Hee Seung Wang1, Jae Hyun Han1, Chang Kyu Jeong2, Keon Jae Lee3
|
| 소속 |
1Korea Advanced Institute of Science and Technology, 2Division of Advanced Materials Engineering, 3Chonbuk National Univ. |
| 키워드 |
Flexible; Piezoelectric; Self-powered; Acoustic sensor; Speaker recognition
|
| E-Mail |
|
