Performance Evaluation of MEMS Vibration Sensors for Throat Microphones
Journal
Proceedings of IEEE Sensors
Part Of
Proceedings of IEEE Sensors
Start Page
1-4
Date Issued
2024-10-20
Author(s)
Che-Yu Hsu
Po-Han Chen
Ting-Yi Chen
Shang-Yu Lin
Ching-Jen Wang
Chingwei Yeh
Tay-Jyi Lin
Abstract
This study demonstrates the development of miniaturized throat microphones using MEMS-based vibration sensors and a voice conversion algorithm. A MEMS-based accelerometer, attached to the throat along with an audio microphone, records the throat vibrations and sound wave data from the TMHINT Mandarin Chinese script, consisting of 320 sentences. The recorded vibration signals are processed to match the microphone signals by an artificial neural network and evaluated using objective metrics such as the Mean Opinion Score (MOS) and Short-Time Objective Intelligibility (STOI). The converted results show that a MEMS vibration sensor with a bandwidth of 2.4 kHz is sufficient for the purpose of voice recovery.
Event(s)
2024 IEEE Sensors, SENSORS 2024, Kobe, 20 October 2024 through 23 October 2024. Code 205267
Subjects
MEMS accelerometers
speech quality assessment
throat microphones
vibration sensors
voice conversion
Publisher
IEEE
Type
conference paper