Citation: Su, Y.; Ma, K.; Zhang, X.;
Liu, M. Neural Network-Enabled
Flexible Pressure and Temperature
Sensor with Honeycomb-like
Architecture for Voice Recognition.
Sensors 2022, 22, 759. https://
doi.org/10.3390/s22030759
Academic Editors: Yangquan Chen,
Subhas Mukhopadhyay, Nunzio
Cennamo, M. Jamal Deen, Junseop
Lee and Simone Morais
Received: 8 December 2021
Accepted: 17 January 2022
Published: 19 January 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Communication
Neural Network-Enabled Flexible Pressure and Temperature
Sensor with Honeycomb-like Architecture for
Voice Recognition
Yue Su
†
, Kainan Ma
†
, Xu Zhang * and Ming Liu *
Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China; yuesu@semi.ac.cn (Y.S.);
makainan@semi.ac.cn (K.M.)
* Correspondence: zhangxu@semi.ac.cn (X.Z.); liuming@semi.ac.cn (M.L.)
† These authors contributed equally to this work.
Abstract:
Flexible pressure sensors have been studied as wearable voice-recognition devices to
be utilized in human-machine interaction. However, the development of highly sensitive, skin-
attachable, and comfortable sensing devices to achieve clear voice detection remains a considerable
challenge. Herein, we present a wearable and flexible pressure and temperature sensor with a
sensitive response to vibration, which can accurately recognize the human voice by combing with
the artificial neural network. The device consists of a polyethylene terephthalate (PET) printed
with a silver electrode, a filament-microstructured polydimethylsiloxane (PDMS) film embedded
with single-walled carbon nanotubes and a polyimide (PI) film sputtered with a patterned Ti/Pt
thermistor strip. The developed pressure sensor exhibited a pressure sensitivity of 0.398 kPa
−1
in the
low-pressure regime, and the fabricated temperature sensor shows a desirable temperature coefficient
of resistance of 0.13%
◦
C in the range of 25
◦
C to 105
◦
C. Through training and testing the neural
network model with the waveform data of the sensor obtained from human pronunciation, the vocal
fold vibrations of different words can be successfully recognized, and the total recognition accuracy
rate can reach 93.4%. Our results suggest that the fabricated sensor has substantial potential for
application in the human-computer interface fields, such as voice control, vocal healthcare monitoring,
and voice authentication.
Keywords:
flexible pressure and temperature sensor; artificial neural network; filament-microstructured;
voice-recognition
1. Introduction
The human voice, as the main medium of communication with the outside world,
plays a significant role in various aspects such as telecommunication, human-machine
interaction, and the Internet of Things [
1
]. Conventional rigid microphones have been
developed for accurately detecting human voice, but their applications are limited in noisy
or windy environments. Recently, the flexible wearable pressure sensors that can provide
electrical feedback in response to external pressure stimuli have been used for monitoring
human voices [
2
–
12
]. By measuring vibrations in users’ neck skin and converting them
into readable signals, these sensors have advantages of clear voice detection and anti-
interference. In order to accurately obtain meaningful acoustic waveform, the sensors based
on various transduction mechanisms have been proposed, including triboelectricity [
2
,
3
],
capacitance [
4
], piezoelectricity [
5
,
6
], and piezoresistivity
[7–10].
Among them, the sensors
that rely on piezoresistivity have attracted much attention due to their simple device assem-
bly and low energy consumption [
11
–
13
]. Although great achievements have been made
in the fabrication of piezoresistive-type sensors, such as skin-conformity and technology
compatibility, achieving high sensitivity in a wide measuring range remains a subject
worthy of intense study.
Sensors 2022, 22, 759. https://doi.org/10.3390/s22030759 https://www.mdpi.com/journal/sensors
