Research on Throat Speech Signal Detection Based on a Flexible Graphene Piezoresistive Sensor

Abstract

Aiming at the problem that traditional speech acquisition and recognition are susceptible to environmental noise, this paper proposes a flexible graphene sensor to detect vocal vibration signals. First, the speech detection sensor with a cylindrical microsurface structure substrate is prepared by chemical vapor deposition (CVD) and imprint technology, which greatly improves the conformal coating cover ability and sensitivity of the sensor. In the range of 200–2500 Hz, the average voltage gain of the sensor is ∼48 dB, and this frequency range basically covers the human speech frequency. On this basis, we conducted a bilingual detection (Chinese and English). All data obtained shows that the graphite speech sensor has sufficient sensitivity to extract the characteristics of acoustic waves. At the same time, the proposed cylindrical microsurface structure reduces the probability of random fracture of the graphene layer. In addition, the speech signals collected by a microphone and the flexible graphene speech detection sensor are used to train a neural network. The recognition accuracy of the data set mixed with vocal cord speech signals is 75.9%. The comparison verifies that the signals detected by the sensor have sufficient characteristic information to complete speech recognition tasks.

Bubbles-Induced Porous Structure-Based Flexible Piezoresistive Sensors for Speech Recognition

“…In 2022, Tong et al used polydimethylsiloxane (PDMS) with columnar structures as a template and covered it with a graphene film prepared via chemical vapor deposition to obtain a flexible piezoresistive sensor with a porous structure. 31 When the sensor was combined with a deep learning model and used for speech recognition, its accuracy reached 75.9%. The preparation of flexible piezoresistive sensors with a porous structure by using the template method is a complex process.…”

“…In the latter, conductive nanomaterials are directly coated on the surface of the porous template by using methods such as dip coating and chemical vapor deposition. In 2022, Tong et al used polydimethylsiloxane (PDMS) with columnar structures as a template and covered it with a graphene film prepared via chemical vapor deposition to obtain a flexible piezoresistive sensor with a porous structure . When the sensor was combined with a deep learning model and used for speech recognition, its accuracy reached 75.9%.…”

Flexible Self-Powered Low-Decibel Voice Recognition Mask

“…As science and technology progress, the TENG's role in signal sensing via vibration has expanded into speech recognition, prompting the need for improved material structure, response speed, sensitivity, noise immunity, and deployment contexts. Notably, its capacity to detect signals through vibration has significantly contributed to advancements in acoustic science [27][28][29][30][31][32][33][34][35][36][37]. For instance, Zheng's team engineered a TENG capable of recognizing road and traffic sounds and deployed it on roads or buildings to differentiate between passing vehicles and structural flaws [38].…”

Templated Laser-Induced-Graphene-Based Tactile Sensors Enable Wearable Health Monitoring and Texture Recognition via Deep Neural Network

“…The template manufacturing approach offers an accessible method to create sensors with adjustable sensing properties. ,, Various nanomicro structured sensing layers, including carbon nanotubes, , Ag nanowires, and graphene, have been investigated using methods such as chemical vapor transport, electrospinning, and drop casting . However, their practical applications remain limited, presumably due to the high cost of nanomicro materials, complex processes, and poor reproducibility.…”