Voice Activity Research Articles

A novel tiny triboelectric acoustic sensor design based on nanocomposite enhancement for highly-sensitive, broadband, and self-powered multi-functional applications

This work proposes a novel acoustic nanocomposite fibrous membrane-based triboelectric nanogenerator (NFM-TENG) with excellent acoustical-to-electrical conversion performance. The optimal combination for the triboelectric pairs of NFM-TENG is identified: a polyvinylidene fluoride-multiwalled carbon nanotubes (PVDF-MWCNTs (1 wt%)) nanofibrous membrane as the tribo-positive layer, and a corona-charged fluorinated ethylene-propylene (FEP) solid membrane as the tribo-negative layer, resulting in higher electric output than single-friction-layered NFM-TENG (32 times). Under the acoustic excitation of 116 dB at 200 Hz, the acoustic NFM-TENG can generate a maximum areal power density of 3.78 W/m2. The NFM-TENG can be used not only as a acoustic energy harvester, but also as a self-powered triboelectric acoustic sensor (TAS) for real-time voice recording and control. For convenience, for the first time, an advanced tiny TAS (TTAS, diameter: only 9.7 mm) based on the NFM-TENG is developed and its sensitivity is calibrated as -50 dB according to the International standard IEC61094. Experimental results also verified that the TTAS with broadband response ability (20–20,000 Hz) is fully competent for commercial applications such as real-time voice control, HMI, and other multi-scenarios. The TTAS is smart, reliable and customizable, potentially leading to a new revolution in intelligent interaction.

Hybridization of metaheuristics and NLP approach to examine public opinion towards virtual voice assistants

Hybridization of metaheuristics and NLP approach to examine public opinion towards virtual voice assistants

Speech Emotion Recognition Method Based on Support Vector Machine and Suprasegmental Acoustic Features

The problem of recognizing emotions in a speech signal using mel-frequency cepstral coefficients using a classifier based on the support vector machine has been studied. The RAVDESS data set was used in the experiments. A model is proposed that uses a 306-component suprasegmental feature vector as input to a support vector machine classifier. Model quality was assessed using unweighted average recall (UAR). The use of linear, polynomial and radial basis functions as a kernel in a classifier based on the support vector machine is considered. The use of different signal analysis frame sizes (from 23 to 341 ms) at the stage of extracting mel-frequency cepstral coefficients was investigated. The research results revealed significant accuracy of the resulting model (UAR = 48 %). The proposed approach shows potential for applications such as voice assistants, virtual agents, and mental health diagnostics.

Deep learning-based dimensional emotion recognition for conversational agent-based cognitive behavioral therapy.

Internet-based cognitive behavioral therapy (iCBT) offers a scalable, cost-effective, accessible, and low-threshold form of psychotherapy. Recent advancements explored the use of conversational agents such as chatbots and voice assistants to enhance the delivery of iCBT. These agents can deliver iCBT-based exercises, recognize and track emotional states, assess therapy progress, convey empathy, and potentially predict long-term therapy outcome. However, existing systems predominantly utilize categorical approaches for emotional modeling, which can oversimplify the complexity of human emotional states. To address this, we developed a transformer-based model for dimensional text-based emotion recognition, fine-tuned with a novel, comprehensive dimensional emotion dataset comprising 75,503 samples. This model significantly outperforms existing state-of-the-art models in detecting the dimensions of valence, arousal, and dominance, achieving a Pearson correlation coefficient of r=0.90, r=0.77, and r=0.64, respectively. Furthermore, a feasibility study involving 20 participants confirmed the model's technical effectiveness and its usability, acceptance, and empathic understanding in a conversational agent-based iCBT setting, marking a substantial improvement in personalized and effective therapy experiences.

A High-Speed Acoustic Echo Canceller Based on Grey Wolf Optimization and Particle Swarm Optimization Algorithms.

Currently, the use of acoustic echo cancellers (AECs) plays a crucial role in IoT applications, such as voice control appliances, hands-free telephony and intelligent voice control devices, among others. Therefore, these IoT devices are mostly controlled by voice commands. However, the performance of these devices is significantly affected by echo noise in real acoustic environments. Despite good results being achieved in terms of echo noise reductions using conventional adaptive filtering based on gradient optimization algorithms, recently, the use of bio-inspired algorithms has attracted significant attention in the science community, since these algorithms exhibit a faster convergence rate when compared with gradient optimization algorithms. To date, several authors have tried to develop high-performance AEC systems to offer high-quality and realistic sound. In this work, we present a new AEC system based on the grey wolf optimization (GWO) and particle swarm optimization (PSO) algorithms to guarantee a higher convergence speed compared with previously reported solutions. This improvement potentially allows for high tracking capabilities. This aspect has special relevance in real acoustic environments since it indicates the rate at which noise is reduced.

Research on Intelligent Wheelchair Multimode Human–Computer Interaction and Assisted Driving Technology

The traditional wheelchair focuses on the “human-chair” motor function interaction to ensure the elderly and people with disabilities’ basic travel. For people with visual, hearing, physical disabilities, etc., the current wheelchairs show shortcomings in terms of accessibility and independent travel for this group. Therefore, this paper develops an intelligent wheelchair with multimodal human–computer interaction and autonomous navigation technology. Firstly, it researches the multimodal human–computer interaction technology of occupant gesture recognition, speech recognition, and head posture recognition and proposes a wheelchair control method of three-dimensional head posture mapping the two-dimensional plane. After testing, the average accuracy of the gesture, head posture and voice control modes of the motorized wheelchair proposed in this study reaches more than 95 percent. Secondly, the LiDAR-based smart wheelchair indoor autonomous navigation technology is investigated to realize the autonomous navigation of the wheelchair by constructing an environment map, using A* and DWA algorithms for global and local path planning, and adaptive Monte Carlo simulation algorithms for real-time localization. Experiments show that the position error of the wheelchair is within 10 cm, and the heading angle error is less than 5° during the autonomous navigation. The multimode human–computer interaction and assisted driving technology proposed in this study can partially compensate and replace the functional deficiencies of the disabled population and improve the quality of life of the elderly and disabled population.

EmoWear: Wearable Physiological and Motion Dataset for Emotion Recognition and Context Awareness

The EmoWear dataset provides a bridge to explore Emotion Recognition (ER) via Seismocardiography (SCG), the measurement of small cardio-respiratory induced vibrations on the chest wall through Inertial Measurement Units (IMUs). We recorded Accelerometer (ACC), Gyroscope (GYRO), Electrocardiography (ECG), Blood Volume Pulse (BVP), Respiration (RSP), Electrodermal Activity (EDA), and Skin Temperature (SKT) data from 49 participants who watched validated emotionally stimulating video clips. They self-assessed their emotional valence, arousal, and dominance, as well as extra questions about the video clips. Also, we asked the participants to walk, talk, and drink, so that researchers can detect gait, voice, and swallowing using the same IMU. We demonstrate the effectiveness of emotion stimulation with statistical methods and verify the quality of the collected signals through signal-to-noise ratio and correlation analysis. EmoWear can be used for ER via SCG, ER during gait, multi-modal ER, and the study of IMUs for context-awareness. Targeted contextual information include emotions, gait, voice activity, and drinking, all having the potential to be sensed via a single IMU.

‘Alexa, play metal’: exploring music selection and personal information management via voice assistants

Introduction. Music streaming services have changed how music is played and perceived, but also how it is managed by individuals. Voice interfaces to such services are becoming increasingly com-mon, for example through voice assistants on mobile and smart devices, and have the poten-tial to further change personal music management by introducing new beneficial features and new challenges. Method. To explore the implications of voice assistants for personal music listening and management we surveyed 248 participants online and in a lab setting to investigate (a) in which situa-tions people use voice assistants to play music, (b) how the situations compare to established activities common during non-voice assistant music listening, and (c) what kinds of com-mands they use. Analysis. We categorised 653 situations of voice assistant use, which reflect differences to non-voice assistant music listening, and established 11 command types, which mostly reflect finding or refinding activities but also indicate keeping and organisation activities. Results. Voice assistants have some benefits for music listening and personal music management, but also a notable lack of support for traditional personal information management activities, like browsing, that are common when managing music. Conclusion. Having characterised the use of voice assistants to play music, we consider their role in per-sonal music management and make suggestions for improved design and future research.

Dependency-aware action planning for smart home.

How can a smart home system control a connected device to be in a desired state? Recent developments in the Internet of Things (IoT) technology enable people to control various devices with the smart home system rather than physical contact. Furthermore, smart home systems cooperate with voice assistants such as Bixby or Alexa allowing users to control their devices through voice. In this process, a user's query clarifies the target state of the device rather than the actions to perform. Thus, the smart home system needs to plan a sequence of actions to fulfill the user's needs. However, it is challenging to perform action planning because it needs to handle a large-scale state transition graph of a real-world device, and the complex dependence relationships between capabilities. In this work, we propose SmartAid (Smart Home Action Planning in awareness of Dependency), an action planning method for smart home systems. To represent the state transition graph, SmartAid learns models that represent the prerequisite conditions and operations of actions. Then, SmartAid generates an action plan considering the dependencies between capabilities and actions. Extensive experiments demonstrate that SmartAid successfully represents a real-world device based on a state transition log and generates an accurate action sequence for a given query.

Voice Over for Home Security System

The Smart Home Voice Control Hub is an advanced, integrated system design to seamlessly manage and operate a variety of smart home devices using voice commands. Recent years have witnessed significant advancements in home automation driven by wireless technologies. Among these, the IEEE 802.15.4 standard, RF, stands out for its low data rate, extended battery lif e, and secure networking capabilities. This article details a method for testing voice control implementation in smart homes, emphasizing compatibility with existing infrastructure. Utilizing low-power RF wireless modules and a microcontroller, the system caters to the needs of elderly and disabled individuals living independently. By focusing on voice recognition, it off ers enhanced security and control over household lighting and appliances. Experimental validation demonstrates the system's effectiveness in practical applications.

Governance and Economic Growth in Selected Sub-Saharan African Countries

The variation in economic growth among nations has brought the issue of economic growth to the forefront. Growth in an economy is key for economic development. When "the country's total earnings increase", its population benefits. Economic growth is significant because it promote the competitiveness of any nation. One of the most striking challenges of economic growth in Sub-Saharan African (SSA) countries is poor governance, decline in the living conditions of the population, with the specter of widespread hunger plaguing people's perceptions. The objective of the study is to examine the effect of governance on economic growth in the selected Sub-Saharan African (SSA) countries. The technique adopted for this study is the Panel Corrected Standard Error Method. This method was employed because it controls for heteroscedasticity. The result shows that there exist a direct relationship between control of corruption, voice and accountability, political stability and absence of violence on real gross domestic product in SSA respectively, while regulatory quality and government effectiveness has a negative effect on real gross domestic product (RGDP) respectively. The study recommends that SSA government as well as stakeholders in the region needs to improve the quality of their regulations and also endeavor to improve on their effectiveness and efficiency.

Will senior adults accept being cognitively assessed by a conversational agent? a user-interaction pilot study

Background: early detection of dementia and Mild Cognitive Impairment (MCI) have an utmost significance nowadays, and smart conversational agents are becoming more and more capable. DigiMoCA, an Alexa-based voice application for the screening of MCI, was developed and tested. Objective: to evaluate the acceptability and usability of DigiMoCA, considering the perception of end-users and cognitive assessment administrators, through standard evaluation questionnaires. Method: a sample of 46 individuals and 24 evaluators participated in this study. End-users were fairly heterogeneous considering demographic and neuro-psychological characteristics. Evaluators were mostly health and social care professionals, relatively well-balanced in terms of gender, career background and years of experience. Results: end-users acceptability ratings were generally positive (rating above 3 in a 5-point scale for all dimensions) and it improved significantly after the interaction with DigiMoCA. Administrators also rated the usability of DigiMoCA, with an average score of 5.86/7 and with high internal consistency (α\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\alpha $$\\end{document} = 0.95). Conclusion: although there is still room for improvement in terms of user satisfaction and voice interface, DigiMoCA is perceived as an acceptable, accessible and usable cognitive screening tool, both by individuals being tested and test administrators.Graphical abstract

The mediating role of governance in creating a nexus between investment in artificial intelligence (AII) and human well-being in the BRICS countries

The BRICS countries (Brazil, Russia, India, China, and South Africa) aim to achieve Sustainable Development Goals 3 and 16, which involve promoting human well-being for all and building strong institutions and governance. This study examines the AII-HWBG nexus contingent on governance indicators within the BRICS nations in 2012-2022 using the Cross-Sectional Augmented Autoregressive Distributed Lag (CS-ARDL) technique. Its findings reveal a long-term relationship among variables with varied causality directions and point to the necessity of integrating governance quality into AII to boost HWBG in both the short- and long-term perspective. Since AII has not so far been used to support HWBG there is a dire need for caution when considering AII’s interaction with institutional governance, economic governance, control of corruption, political stability, regulatory quality and voice and accountability. The paper highlights the crucial role of governance quality in shaping the way AI investment impacts the human well-being. To ensure an overall improvement of well-being, priority should be given to strategies that promote positive synergy between AI investment and governance while mitigating possible harmful effects. Carefully targeted measures in governance areas can create an environment conducive to AI development where it will significantly benefit the citizens of the BRICS countries.

The AI humanness: how perceived personality builds trust and continuous usage intention

PurposeThe growing integration of artificial intelligence (AI) assistants and voice assistants provides a platform for AI to enter consumers’ everyday lives. As these voice assistants become ubiquitous, their widespread adoption underscores the need to understand how to create voice assistants that can naturally interact with and support users. Grounded in the stereotype content model from social psychology, this study aims to investigate the influence of perceived humanness and personality on building trust and continuous usage intentions in voice assistants. Specifically, a fresh perspective examining the determining factors that shape personality trait perceptions of competence and warmth in voice assistants is proposed.Design/methodology/approachAn online survey of 457 participants and structural equation modeling is conducted to validate the research model.FindingsAnthropomorphism, social presence and interactivity drive perceived warmth, whereas performance and effort expectations drive perceived competence. Perceived competence and perceived warmth together positively affect users’ trust in voice assistants, leading to a higher likelihood of continuous usage intentions.Originality/valueThis research provides profound theoretical contributions to the emerging field of human-AI interaction and offer practical implications for marketers aiming to leverage voice assistant personalities to build trusted and long-lasting interactions.

Acceptance and use of artificial intelligence and AI-based applications in education: A meta-analysis and future direction

The aim of present study was to measure the relationship of UTAUT (Unified Theory of Acceptance and Use of Technology) and TAM (Technology Acceptance Model) variables regarding AI technology and AI-based applications acceptance in education sector. Research was carried out by using PRISMA (Preferred reporting items for systematic review and meta-analysis) guidelines. The relevant studies were searched from major databases that included a) Scopus, and b) Web of Science. Initial search retrieved 309 titles, and 30 relevant articles and conference papers were selected following the search process. Data was analysed using CMA (Comprehensive Meta-analysis) and Meta-Essential software. Findings exhibit that the relationship between UTAUT variables and BI to accept AI and AI-based applications in education was high (PE → BI), medium (EE → BI, SI → BI), and low (FC → BI). The magnitude of the relationship of TAM constructs remained high for all paths (PU → AT, PEOU → AT, PU → BI, and PEOU → BI). Theoretically, this meta-analysis provided a panoramic picture of two leading technology acceptance models regarding the acceptance/adoption of AI and AI-based technology in education sector. This meta-analysis provided a way forward for researchers to extend research on AI-based applications including ChatGPT, intelligent tutoring, AI-based robots, AI-based Chatbots, and AI-based voice assistants. Practically, findings are useful for IT companies, and decision makers of educational institutes in designing and implementing AI and AI-based applications.

Importance Performance Matrix Analysis for Assessing User Experience with Intelligent Voice Assistants: A Strategic Evaluation

Importance Performance Matrix Analysis for Assessing User Experience with Intelligent Voice Assistants: A Strategic Evaluation

Design and Implementation of an IOT-based Smart Home Automation System in Real World Scenario

INTRODUCTION: Automation developments have significantly increased general convenience in modern technology. Our study focuses on developing and deploying an Internet of Things (IoT)–enabled smart home automation system that maximizes energy efficiency and improves convenience in residential settings. Our technology provides homes with an intelligent environment by smoothly combining several sensors, actuators, and communication protocols. We explore the challenges of creating a reliable and useful smart home systemthat works well in everyday situations. We investigate the difficulties, architectural issues, communication protocols, and security features specific to these systems.OBJECTIVES: This project aims to use a database server and Wi-Fi module to develop an effective and reasonably priced smart home automation system. It improves accessibility and convenience by enabling smartphone voice control of household appliances.METHODS: This project was developed using various implementation techniques, including wireless home automation via GSM technology, speech recognition-based systems, Blynk, and the Internet of Things. These techniques added up to a reliable and effective smart home system.RESULTS: Although it improved user routines, the IoT-based smart home system had latency problems. Interoperability issues are still present. Improvements were guided by user input. Using Blynk, our software manages loads remotely. CONCLUSION: A home automation system that is inexpensive and locally supplied can effectively operate household appliances. It is adaptable, scalable, and a component of future smart homes. IoT applications in real life revolutionize convenience and efficiency in living environments.

Types of AI and Their Suitability for Performing Daily Activities

Abstract The usage of robots and artificial intelligence in the business field and in the everyday life of consumers has been a topic of discussion for a long time. While some people are fascinated by the opportunity of having robots supporting them in their daily activities, others are more hesitant. Nowadays, there are different types of robots with artificial intelligence, and consumers, depending on their preferences and needs, prefer a certain type of robot. With the help of an online survey, we found out which type of robot is most often used by the consumer and why. Among the various types of robots with artificial intelligence that were mentioned in the questionnaire, personal home assistants are the robot with artificial intelligence that consumers prefer when they want to perform an action. The second most preferred robot with artificial intelligence is the self-service portal with AI, and in third place is the personal voice assistant. The main results show that personal home assistants are robots with artificial intelligence, which is used most often by the consumer to order food, different products and to perform different activities. With the help of the results, we can also observe that consumers also use the self-service portal with AI as a navigation system or as an alarm clock. The personal voice assistant is the type of artificial intelligence robot that is least used by consumers to do something, which is again an important result.

EchoTap: Non-Verbal Sound Interaction with Knock and Tap Gestures

The growing demand for highly accessible interaction technologies to effectively interact with smart devices has led to the increasing popularity of voice user interfaces (VUIs). However, VUIs face interpretation challenges stemming from the variability of natural language input, such as speech clarity issues, linguistic variability, and speech impediments. As an alternative, non-verbal sound-based interaction techniques emerge as highly advantageous for smart device control, mitigating the inherent challenges of VUIs. In this article, we introduce EchoTap, a novel audio interface that harnesses the distinctive sound responses generated by knock and tap gestures on target objects. Employing deep neural networks, EchoTap recognizes both the type and location of these gestures based on their unique sound signatures. Through offline evaluation, EchoTap demonstrated competitive classification accuracy (88% on average) and localization precision (93% on average). Moreover, a user study involving 12 participants validated EchoTap’s practical effectiveness and user-friendliness in real-world scenarios. This study highlights EchoTap’s potential for various daily interaction contexts and discusses further design implications for leveraging auditory interfaces based on simple gestures.

AURA-The Privacy Preserving Multifunctional Desktop Voice Assistant

Abstract: The “AURA” is the project which proposes the development of the versatile desktop voice assistant which mainly focuses on the privacy of the user.The convenience of voice interaction has surged in popularity, but concerns about user privacy remain. Conventional cloud-based voice assistants raise anxieties regarding data collection, storage, and potential misuse. This survey paper explores the burgeoning field of privacy-preserving desktop voice assistants powered by Artificial Intelligence (AI). We delve into the core challenges of on-device speech recognition, natural language understanding, and response generation while maintaining user privacy. We conclude by outlining open research questions and future directions for this evolving field, paving the way for the development of secure and user-centric voice interaction experiences on desktops.