Microphone Sensor Research Articles

Disturbances in Electrodermal Activity Recordings Due to Different Noises in the Environment.

Electrodermal activity (EDA) is a widely used psychophysiological measurement in laboratory-based studies. In recent times, these measurements have seen a transfer from the laboratory to wearable devices due to the simplicity of EDA measurement as well as modern electronics. However, proper conditions for EDA measurement are recommended once wearable devices are used, and the ambient conditions may influence such measurements. It is not completely known how different types of ambient noise impact EDA measurement and how this translates to wearable EDA measurement. Therefore, this study explored the effects of various noise disturbances on the generation of EDA responses using a system for the simultaneous recording of all measures of EDA, i.e., skin conductance responses (SCRs), skin susceptance responses (SSRs), and skin potential responses (SPRs), at the same skin site. The SCRs, SSRs, and SPRs due to five types of noise stimuli at different sound pressure levels (70, 75, 80, 85, and 90 dB) were measured from 40 participants. The obtained results showed that EDA responses were generated at all levels and that the EDA response magnitudes were significantly (p < 0.001) influenced by the increasing noise levels. Different types of environmental noise may elicit EDA responses and influence wearable recordings outside the laboratory, where such noises are more likely than in standardized laboratory tests. Depending on the application, it is recommended to prevent these types of unwanted variation, presenting a challenge for the quality of wearable EDA measurement in real-world conditions. Future developments to shorten the quality gap between standardized laboratory-based and wearable EDA measurements may include adding microphone sensors and algorithms to detect, classify, and process the noise-related EDA.

Multisensory Fusion for Unsupervised Spatiotemporal Speaker Diarization.

Speaker diarization consists of answering the question of "who spoke when" in audio recordings. In meeting scenarios, the task of labeling audio with the corresponding speaker identities can be further assisted by the exploitation of spatial features. This work proposes a framework designed to assess the effectiveness of combining speaker embeddings with Time Difference of Arrival (TDOA) values from available microphone sensor arrays in meetings. We extract speaker embeddings using two popular and robust pre-trained models, ECAPA-TDNN and X-vectors, and calculate the TDOA values via the Generalized Cross-Correlation (GCC) method with Phase Transform (PHAT) weighting. Although ECAPA-TDNN outperforms the Xvectors model, we utilize both speaker embedding models to explore the potential of employing a computationally lighter model when spatial information is exploited. Various techniques for combining the spatial-temporal information are examined in order to determine the best clustering method. The proposed framework is evaluated on two multichannel datasets: the AVLab Speaker Localization dataset and a multichannel dataset (SpeaD-M3C) enriched in the context of the present work with supplementary information from smartphone recordings. Our results strongly indicate that the integration of spatial information can significantly improve the performance of state-of-the-art deep learning diarization models, presenting a 2-3% reduction in DER compared to the baseline approach on the evaluated datasets.

A self-powered metamaterial augmented nanogenerator for low-frequency acoustic telecommunication

This study introduces a novel self-powered metamaterial augmented nanogenerator for low-frequency acoustic telecommunication (MANLAT), which is designed to enhance acoustic communication capabilities by utilizing the local resonance mechanism to selectively amplify specific frequency bands of incident sound and generate large amplitude signals in a self-powered manner. The MANLAT device consists of a flexible bottom that responds to pressure differences by generating strong vibrations. Additionally, a lightweight cone-shaped component is attached to the central part of the flexible plate, thus increasing the surface area in that region. Through contact electrification and electrostatic induction mechanisms, a substantial electrical signal is generated, allowing the device to serve as a self-powered acoustic telecommunication receiver. To assess its performance in real-world scenarios, environmental interference was simulated by generating white noise added to the modulated waveform containing information, which was then transmitted through a loudspeaker. At the receiving end, a high-precision microphone sensor was used alongside the MANLAT device to capture the sound wave. The experimental results demonstrate that the MANLAT device surpassed the microphone sensor in mitigating noise interference and enabled the effective decoding of information even in the presence of high levels of white noise or background music. Consequently, the device simplifies communication systems, facilitates reliable and environmentally friendly communication, and enhances information security.

Local Culture Integration in Physics Experiments: Exploring Angklung with Arduino-Enhanced Frequency Measurement

Experimental activities in physics learning are important to encourage students to interact directly with physical phenomena. This study integrates local culture with technology through an innovative approach to the design of physics experiments. Arduino, a low-cost microcontroller, is extensively utilized for learning physics. The local culture examined in this study is Angklung, a traditional musical instrument from West Java, Indonesia. This study utilizes Arduino with a microphone sensor to design experiments investigating the sound produced by Angklung. The experimental activity aims to determine the frequency generated on each musical instrument on the diatonic Angklung and the factors that influence that frequency. The experimental results show that each musical instrument has a different frequency. Programming on Arduino is easy for students even though students do not have basic programming knowledge. The results of this study can be used as a reference for conducting alternative experiments using affordable equipment and objects familiar to students.

A Feedback Active Control Approach to Road Noise Based on a Single Microphone Sensor to Improve Automotive Cabin Sound Comfort.

Tire-road noise deteriorates the sound quality of a vehicle's interior and affects the driving safety and comfort. Obtaining low interior noise is a challenge for passenger car manufacturers. Traditional passive noise control (PNC) is efficient for canceling high frequency noise but not useful for low frequency noise, while active noise control (ANC), according to the residual error signal, can generate an anti-noise signal to reduce the original noise. Most research has focused on improving the control effect for a feedforward ANC system. However, this paper emphasizes a feedback ANC system based on a signal microphone sensor. There are two main contributions in this study to improve automotive cabin sound comfort. One is that the algorithm of the feedback ANC system using a single microphone sensor without a reference noise signal is proposed based on the Filtered-x Least Mean Square method. The other is that the algorithm applies additive random noise online to estimate the secondary path model. A simulation was implemented based on measured real road noise data, and the simulation results indicate that the proposed feedback ANC system with the single microphone sensor can effectively attenuate road noise. This study shows the feasibility of applying a feedback ANC system in automobiles to increase the cabin sound quality.

Improved Accuracy in Determining the Acceleration Due to Gravity in Free Fall Experiments Using Smartphones and Mechanical Switches

This study presents an innovative methodology to augment the accuracy of gravitational acceleration (g) measurements in free fall experiments. Employing smartphones and integrating mechanical switches, our approach utilizes a built-in microphone for precise time measurements during the initiation of free fall. A meticulously designed mechanical switch controls the release of a steel sphere, triggering the timer upon the initiation of descent. Our experimental outcomes showcase a commendable congruence between the calculated g value and the locally accepted reference value, pinpointing g at 9.8274 ± 0.01 m/s2. A salient feature of our method is the utilization of the smartphone’s onboard microphone sensor, offering superior convenience to conventional sensor-based methodologies that require additional equipment. Additionally, our study introduces the seamless integration of open-source software on smartphones, facilitating the direct display and analysis of sound parameters. This integration streamlines the experimental process, contributing to the ongoing endeavors aimed at enhancing accuracy in free fall experiments. Our findings underscore the potential of smartphones and mechanical switches as accessible and effective tools in advancing physics education and scientific investigations.

A high-performance infrared photoacoustic sensor with improved low-frequency response microphone

Infrared photoacoustic gas sensors with the advantages of good selectivity, low interference, fast response speed, good stability, high accuracy, good explosion-proof performance, high signal-to-noise ratio, and long service life, have developed rapidly in recent years. In order to solve the problem of poor low-frequency response performance of the MEMS piezoelectric thin film microphone sensor prepared with AlN and Mo thin films in infrared photoacoustic gas sensors, this article analyzes its principle and tests an improved solution. The internal stress distribution was changed through hot tempering experiments, significantly improving its structure. The article qualitatively and quantitatively analyzes the inherent mechanism of this phenomenon. The experimental results confirm that the improved scheme improves its response performance under low-frequency signals, with good stability and repeatability.

Detecting Rice Weevils in Stored Grains using MFCC and CNN

Sitophilus oryzae or commonly known as Rice Weevil is a pest that infests stored rice grains. The feeding and movement of this pest within the grain produce sounds that are audible to a high-performance microphone sensor. This study presents a method for early detection of Rice Weevils based on the frequency of the sound they produce. Sound features were extracted using MFCC and utilized as input features to train a Convolutional Neural Network (CNN). The classifier was evaluated using 2800 acoustic samples containing positive and negative datasets. The experimental results show that the method can be an alternative approach for the early detection of the presence of rice weevils in stored rice grains.

SensiX++: Bringing MLOps and Multi-tenant Model Serving to Sensory Edge Devices

We present SensiX++, a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e.g., a camera, a microphone, or IoT sensors. SensiX++ operates on two fundamental principles: highly modular componentisation to externalise data operations with clear abstractions and document-centric manifestation for system-wide orchestration. First, a data coordinator manages the lifecycle of sensors and serves models with correct data through automated transformations. Next, a resource-aware model server executes multiple models in isolation through model abstraction, pipeline automation, and feature sharing. An adaptive scheduler then orchestrates the best-effort executions of multiple models across heterogeneous accelerators, balancing latency and throughput. Finally, microservices with REST APIs serve synthesised model predictions, system statistics, and continuous deployment. Collectively, these components enable SensiX++ to serve multiple models efficiently with fine-grained control on edge devices while minimising data operation redundancy, managing data and device heterogeneity, and reducing resource contention. We benchmark SensiX++ with 10 different vision and acoustics models across various multi-tenant configurations on different edge accelerators (Jetson AGX and Coral TPU) designed for sensory devices. We report on the overall throughput and quantified benefits of various automation components of SensiX++ and demonstrate its efficacy in significantly reducing operational complexity and lowering the effort to deploy, upgrade, reconfigure, and serve embedded models on edge devices.

Phased array microphone measurement of a ducted low-speed axial flow fan at various operating points with the involvement of the acoustically transparent duct technique

The aeroacoustic investigation of ducted turbomachines is not evident. Wall-mounted and strut-mounted microphones placed in the flow field are both sensitive to installation, placement, and flow-related effects. Therefore, it is advantageous to place the microphone sensors outside of the ducting of the turbomachine while also accounting for the acoustic characteristic of the ducting. In this paper, a ducted low-speed axial flow fan is investigated with the acoustically transparent duct (ATD) and the phased array microphone (PAM) Rotating Source Identification (ROSI) beamforming techniques at design and off-design conditions. The combination of these methods is capable of identifying the dominant sound sources of the fan in a non-intrusive approach at stall condition, pre-stall operation, design condition, and part-load operating condition as well.

Acoustic signal-based indigenous real-time rainfall monitoring system for sustainable environment

The rainfall weather station employs a tipping bucket rain gauge, which serves as a specialized instrument for the meticulous assessment and documentation of various rainwater parameters. The implementation of a tipping bucket rain gauge for rainfall monitoring bears significant implications for both societal productivity as well as improvement of human life. A noteworthy example can be the constructive influence of rainwater over the sustainable agricultural irrigation practices, wherein the precise monitoring of rainfall through a tipping bucket rain gauge enables the formulation of tedious irrigation strategies. The rainfall monitoring if often handle using rain gauge which majorly faces two challenges named as mechanical devices failure and high installation and maintenance cost. Considering the challenges, we propose the fully automated rain gauge (RG) based on the principle of sound and its properties for rainfall monitoring. The working prototype is part of our work whose primary task is to collect the rainfall acoustic value and store it in the cloud. Our mechanism is to use the acoustic property of rain data to categorize rainfall intensity. We perform blind signal separation on the received signal (acoustic signal recorded with the help of microphone sensor) and feed the separated signal to a recurrent convolution neural network (RCNN). The source separation of the collected acoustic signals is primarily being done using independent component analysis and principal components analysis. The proposed solution can be able to make the classification of rain intensity with more than 80% accuracy. In addition to this, the developed method provides the sustainable solution to the challenges with the low-cost and application-specific acceptable threshold criteria and supplement rain measurement techniques.

Low level detection of acetone vapor by improvised design of high “Q” tunable frequency Helmholtz photoacoustic cell using UV, mid- IR and THz sources

The paper reports the designing and fabrication aspects of a high “Q = 492.3” Helmholtz photoacoustic (PA) cell employed for the trace level detection of acetone, a biomarker by using 266 nm- UV, Mid-IR (5.4–10.6 micron) and 0.11 Terahertz (THz) sources. The designed Helmholtz PA cell is made of Aluminum and possesses a natural frequency tunable between 1.4 to 4.4 kHz range using a movable piston arrangement of the microphone sensor. Numerous types of disorders, including diabetes, asthma, lung cancer, etc., can be diagnosed using the acetone concentration obtained through breath analysis. The comparative study is related to the response of different types of excitation mechanisms contributed by electronics, vibrational and rotational modes of acetone. The low-level detection (LoD) limit for acetone is of the order of 5.06 & 7.92 ppbV, and 15.3 pptV, respectively, in UV, Mid-IR, and THz region. This study contributes to the development of a highly sensitive, non-invasive acetone detection and quantification modality.

Comparison of Acoustic Performance of Different Sensors for the Purposes of On-Body Auscultation in Noisy Environments

Lung auscultation is a widely used clinical tool for quick physical assessment of the respiratory system. The ideal sensor preferable for lung auscultation would have high sensitivity to body-conducted sounds with a good resilience to airborne noise. This work envisions to benchmark different sensors starting from air coupled microphones, a bone conduction microphone and PVDF (Polyvinylidene difluoride) sensors on a small chest simulator in a controlled environment. The purpose of this work is to assess the suitability of different sensors, which could be used for lung auscultation both in silent and noisy environments. The proposed work evaluates the performance of different kinds of sensors in terms of their frequency response, noise resilience and a quality metric that expresses sensor’s robustness to airborne noise.

Respiratory Rate Estimation during Walking and Running Using Breathing Sounds Recorded with a Microphone.

Emerging evidence suggests that respiratory frequency (fR) is a valid marker of physical effort. This has stimulated interest in developing devices that allow athletes and exercise practitioners to monitor this vital sign. The numerous technical challenges posed by breathing monitoring in sporting scenarios (e.g., motion artifacts) require careful consideration of the variety of sensors potentially suitable for this purpose. Despite being less prone to motion artifacts than other sensors (e.g., strain sensors), microphone sensors have received limited attention so far. This paper proposes the use of a microphone embedded in a facemask for estimating fR from breath sounds during walking and running. fR was estimated in the time domain as the time elapsed between consecutive exhalation events retrieved from breathing sounds every 30 s. Data were collected from ten healthy subjects (both males and females) at rest and during walking (at 3 km/h and 6 km/h) and running (at 9 km/h and 12 km/h) activities. The reference respiratory signal was recorded with an orifice flowmeter. The mean absolute error (MAE), the mean of differences (MOD), and the limits of agreements (LOAs) were computed separately for each condition. Relatively good agreement was found between the proposed system and the reference system, with MAE and MOD values increasing with the increase in exercise intensity and ambient noise up to a maximum of 3.8 bpm (breaths per minute) and -2.0 bpm, respectively, during running at 12 km/h. When considering all the conditions together, we found an MAE of 1.7 bpm and an MOD ± LOAs of -0.24 ± 5.07 bpm. These findings suggest that microphone sensors can be considered among the suitable options for estimating fR during exercise.

Digital Twin-Driven Tool Condition Monitoring for the Milling Process

Exact observing and forecasting tool conditions fundamentally affect cutting execution, bringing further developed workpiece machining accuracy and lower machining costs. Because of the unpredictability and time-differing nature of the cutting system, existing methodologies cannot achieve ideal oversight progressively. A technique dependent on Digital Twins (DT) is proposed to accomplish extraordinary accuracy in checking and anticipating tool conditions. This technique builds up a balanced virtual instrument framework that matches entirely with the physical system. Collecting data from the physical system (Milling Machine) is initialized, and sensory data collection is carried out. The National Instruments data acquisition system captures vibration data through a uni-axial accelerometer, and a USB-based microphone sensor acquires the sound signals. The data are trained with different Machine Learning (ML) classification-based algorithms. The prediction accuracy is calculated with the help of a confusion matrix with the highest accuracy of 91% through a Probabilistic Neural Network (PNN). This result has been mapped by extracting the statistical features of the vibrational data. Testing has been performed with the trained model to validate the model’s accuracy. Later, the modeling of the DT is initiated using MATLAB-Simulink. This model has been created under the data-driven approach. The physical–virtual balance of the DT model is acknowledged utilizing the advances, taking into consideration the detailed planning of the constant state of the tool’s condition. The tool condition monitoring system through the DT model is deployed through the machine learning technique. The DT model can predict the different tool conditions based on sensory data.

MASTER: Microphone Array Source Time Difference Eco Canceller via Reconstructed Spiking Neural Network

In a real-time environment, background noise frequently makes it harder for listeners to understand speech. Several speech enhancement algorithms based on supervised learning have been applied to improve the clarity and quality of speech. However, neural network-based speech enhancement techniques focus on the magnitude spectrogram while ignoring the phase misalignment between the noisy and clean voice samples. The primary goal of the proposed method is to boost learning language, eliminate echo, and enhance audio quality. In this paper Microphone sensor Array Source Time Difference, Eco canceller via Reconstructed Spiking neural network (MASTER) has been proposed. Initially, the input signals are pre-processed using Hanning Windowing & second-order Butterworth bandpass Filter. The direction of the preprocessed input signal is calculated based on the time delay of the source received between the microphone sensor pairs. The Direction of Arrival (DOA) of the input source is fed into the Reconstructed spiking Convolutional Neural network (RSpiCN Net) that consists of three modules namely spike generation, Masking, and reconstruction for classifying the signals into desired and interference sources. The interference source is fed into an Adaptive Least Mean Square (ALMS) Filter algorithm to get the enhanced signal from the selected source. The proposed method yields better SNR of 7.2 dB, SDR of 6.2 dB, SIR of 8 dB, and PESQ of 2.6 compared to the existing method. The SDR of the proposed method is 3.5%, 4.56%, and 7.85% better than the existing FLANN, R-CED, and Cycle GAN respectively.

Recent Advances in Artificial Intelligence Sensors

AbstractSignificant growth in the development and deployment of artificial intelligence (AI) is being witnessed. Driven by the great versatility of emerging computer science and material science, various AI sensors provide cost‐effective approaches for a wide range of monitoring applications toward the realization of smart homes and personal healthcare. Advanced AI sensors have multiple sensors capable of detecting multidimensional information and human‐brain‐like computation device for data processing. Herein, this review outlines the recent advances in the development of AI sensors. This review first introduces the materials, fabrication methods, and algorithms of current AI sensors and their applications, i.e., complementary metal oxide semiconductor image sensors for computer vision, microelectromechanical systems, microphone sensors for voice recognition, and wearable sensors for gesture recognition. Then, the recent advances in AI wearables sensors and self‐powered sensor systems are highlighted. Next, the current developments of neuromorphic computing systems, multimodality, and digital twins are reviewed. Last, a perspective on future directions for further research development is also provided. In summary, the trend of advanced AI sensors is the complementary between edge computing and cloud computing, which will show great potential in the applications of smart buildings, individual healthcare, the Internet of things, etc.

Snake ecdysis: A potential e-material for advanced electronic technology

Nature has gifted superior e-materials to many living organisms. This work investigates a keratinized hexagonal patterned snake ecdysis for advanced electronic applications. The snake ecdysis carries high porosity, flexibility, piezo-sensitivity, and tribopositivity. Furthermore, the presence of various functional groups and high keratinization are responsible for the piezo and triboelectric properties. First, we develop high-performance and impressively stable piezoelectric and triboelectric energy harvesters based on snake ecdysis. The snake ecdysis-based piezoelectric device is further utilized for various electronic applications such as speaker, microphone, and speech recognition sensor because of its outstanding wide band sensitivity. In addition, the snake ecdysis is further employed as a separator in a piezoelectric supercapacitor. The snake ecdysis/rGO-based piezoelectric supercapacitor delivers an excellent specific capacitance of 82 mF/cm2 with 72 mJ/cm2 energy density. These results suggest that snake ecdysis for energy harvesting, sensing, and storage applications could be an encouraging approach towards snake biodiversity as well as for developing sustainable self-driven electronic devices.

Determining Obstruction in Endotracheal Tubes Using Physical Respiratory Signals

This study proposes a method for determining obstruction of the endotracheal tube (ET) and its degree and location. Respiratory signals were acquired using a three sensor (microphone, pressure, and flow) integrated sensor connector. Obstruction classification involved pre-processing and feature extraction. During pre-processing, one cycle of the respiratory signal was extracted using respiratory cycle extraction and phase segmentation. The signal was then divided into three phases: (i) inspiratory phase, (ii) expiratory phase, and (iii) between both the phases, where the intrapulmonary pressure increased, decreased, and remained constant, respectively. In the feature extraction process, the results were quantified using absolute value average and texture analyses. Artificial ET tubes were fabricated to simulate the presence of foreign substances in the ET tube; they had different degrees of obstruction (0%, 20%, 40%, and 50%) and obstruction positions (Sections 1, 2, and 3). The experiment was performed by connecting the sensor connector and artificial ET tube between the ventilator and test lung. Respiratory signals were obtained in 10 cases by cross connecting the artificial ET tubes. The degree and location of obstruction were classified according to the average absolute value and texture analyses of the flow data. The obstruction can be determined through the texture analysis results using the combined microphone and flow sensor data. The proposed method is simple in configuration, can be readily used in existing setups, and can be operated regardless of surrounding noise.

In the Arms of a Robot: Designing Autonomous Hugging Robots with Intra-Hug Gestures

Hugs are complex affective interactions that often include gestures like squeezes. We present six new guidelines for designing interactive hugging robots, which we validate through two studies with our custom robot. To achieve autonomy, we investigated robot responses to four human intra-hug gestures: holding, rubbing, patting, and squeezing. A Total of 32 users each exchanged and rated 16 hugs with an experimenter-controlled HuggieBot 2.0. The robot’s inflated torso’s microphone and pressure sensor collected data of the subjects’ demonstrations that were used to develop a perceptual algorithm that classifies user actions with 88% accuracy. Users enjoyed robot squeezes, regardless of their performed action, they valued variety in the robot response, and they appreciated robot-initiated intra-hug gestures. From average user ratings, we created a probabilistic behavior algorithm that chooses robot responses in real time. We implemented improvements to the robot platform to create HuggieBot 3.0 and then validated its gesture perception system and behavior algorithm with 16 users. The robot’s responses and proactive gestures were greatly enjoyed. Users found the robot more natural, enjoyable, and intelligent in the last phase of the experiment than in the first. After the study, they felt more understood by the robot and thought robots were nicer to hug.