Silent Speech Recognition with Strain Sensors and Deep Learning Analysis of Directional Facial Muscle Movement

Abstract

Silent communication based on biosignals from facial muscle requires accurate detection of its directional movement and thus optimally positioning minimum numbers of sensors for higher accuracy of speech recognition with a minimal person-to-person variation. So far, previous approaches based on electromyogram or pressure sensors are ineffective in detecting the directional movement of facial muscles. Therefore, in this study, high-performance strain sensors are used for separately detecting x- and y-axis strain. Directional strain distribution data of facial muscle is obtained by applying three-dimensional digital image correlation. Deep learning analysis is utilized for identifying optimal positions of directional strain sensors. The recognition system with four directional strain sensors conformably attached to the face shows silent vowel recognition with 85.24% accuracy and even 76.95% for completely nonobserved subjects. These results show that detection of the directional strain distribution at the optimal facial points will be the key enabling technology for highly accurate silent speech recognition.

A Piezoelectric MEMS Speaker with a Combined Function of a Silent Alarm

“…In actuality, it may not be feasible for individuals to vocalize for assistance or raise an audible alarm when confronted with a potential kidnapping or involuntary confinement, as doing so may provoke hostile parties. Thus, the development of a silent alarm sensor represents a meaningful and promising technological advancement [ 43 , 44 ]. In order to expand the application of piezoelectric MEMS speaker, this proposed device was attempted to be used as a silent alarm sensor, and the working mechanism is shown in Figure 5 a.…”

Machine learning and analytical methods for single-molecule conductance measurements

“…However, RNNs are applicable to variable-length input data such as speech identification. 163 In this method, RNNs were trained on normalised minimum cross-sectional time series data from MD simulations, and a class of experimental conductance traces was predicted. The results showed that RNNs classify variable-length traces and provide a tool for recognising characteristic motifs in traces that are difficult to find using simple data-selection algorithms.…”

All-Optical Diffractive Deep Neural Networks Enabled Laser-Reduced Graphene Oxide Tactile Sensor for Braille Recognition

“…AI systems have found extensive applications in various domains, including healthcare, − finance, − transportation, − manufacturing, , among others. In the fields of artificial intelligence and computer science, deep learning has been widely employed for computer vision, , speech/image recognition, , human–computer interaction systems, , and biomedical image processing, , owing to its advantages in automatic feature learning, adaptability to complex tasks, and large-scale data processing. Traditional deep learning faces limitations such as susceptibility to electromagnetic interference, high energy consumption, and physical constraints. , The faster speed of light compared to electrons, coupled with the diverse information-carrying capacity and types, along with high parallelism and strong resistance to interference, endow all-optical deep learning with tremendous potential and prospects in information transmission and optical computing. − …”