Ti3C2Tx Composite Aerogels Enable Pressure Sensors for Dialect Speech Recognition Assisted by Deep Learning

Abstract

Highlights Emphasized the innovation in both the material design and methodology between the sensing performance and mechanical properties. The composite aerogel pressure sensors exhibited low hysteresis (13.69%), wide detection range (6.25 Pa-1200 kPa), and cyclic stability to acquire stable and accurate pronunciation signals. Over 6888 and 4158 pronunciation signals were collected by the pressure sensor and utilized for training the convolutional neural network model, allowing for accurate recognition of six dialects (96.2% accuracy) and seven words (96.6% accuracy).

Keywords

• Pressure sensor
• Wearable sensor
• Ti3C2Tx composite aerogel
• Dialect speech recognition