Search Results (64)

Real-time speaker localization and speech enhancement remain challenging for embedded acoustic systems operating in noisy and reverberant environments. This paper presents a multichannel beamforming framework based on Generalized Cross-Correlation with Phase Transform (GCC-PHAT) for Direction of Arrival (DOA) estimation and Delay-and-Sum (DAS) beamforming using a compact four-element circular MEMS microphone array. The proposed approach incorporates DOA smoothing and verification to improve localization stability before beamforming. Experimental evaluation in a controlled indoor environment demonstrated localization errors below 1°, while the beamforming stage achieved Signal-to-Noise Ratio (SNR) values predominantly between 25 dB and 40 dB, with peaks approaching 45 dB, and Root Mean Square Error (RMSE) values below 0.05 for most processing windows with an average processing time per frame of 3.473 ms and a memory consumption of 67.11 KB. Comparative results show that the proposed system provides competitive localization accuracy with a computationally simple processing pipeline, making it suitable for real-time embedded applications such as intelligent voice interfaces, videoconferencing systems, and service robotics. Full article

This paper presents an evaluation of AI-assisted human–computer interaction for mathematical problem solving within a multimodal mathematical editing environment. The proposed architecture integrates a visual equation editor, voice-based interaction, REST communication services, and externally hosted generative AI large language models (LLMs) to support the creation, interpretation, and solution of mathematical expressions. The study was conducted using the Equation Wizard environment, which provides multimodal mathematical content editing based on both proprietary and standard formula representations, including MathML and LATEX. A conversational AI interaction layer enables users to communicate with selected LLMs using natural language voice commands. The main objective of the study was to determine whether contemporary LLM-based services can reliably support mathematical problem solving within an AI-enhanced equation editing environment. To address this objective, seven contemporary GenAI LLMs were evaluated using a benchmark consisting of representative high school mathematics problems covering algebra, limits, trigonometry, logarithms, inequalities, and parameterized expressions. The evaluation focused on mathematical correctness, output interpretability and visualization quality, response latency, and compliance with mathematical encoding formats within the complete interaction workflow. The study also compares representative model families with respect to correctness, syntactic compliance, and responsiveness within the complete interaction workflow. Unlike conventional LLM benchmarks that assess models in isolation, this work evaluates end-to-end AI-assisted mathematical interaction involving the editor, communication infrastructure, and language models. The study demonstrates a practical approach to assessing the usefulness of multimodal AI-enhanced mathematical problem solving in realistic usage scenarios. The results show that, within the evaluated interaction workflow, current LLMs achieve high levels of mathematical problem-solving performance, although substantial differences were observed in response latency and output-format compliance. An important finding is the discrepancy between the models’ strong semantic understanding of custom-encoded mathematical input and their weaker ability to generate syntactically compliant encoded outputs, highlighting a key challenge in the integration of LLMs with structured mathematical software environments. Full article

Artificial intelligence (AI) marketing technologies are reshaping customer engagement in service sectors, yet their performance within integrated digital ecosystems remains poorly understood. Existing research often examines AI tools in isolation, overlooking how the holistic quality of the virtual customer experience (VCE) shapes their impact on consumer decisions, particularly in intangible service contexts such as telecommunications. This study addresses this gap by investigating the influence of four AI technologies—chatbots, dynamic pricing, voice search, and visual search—on purchasing decisions, with VCE tested as a critical moderating mechanism. Using Partial Least Squares Structural Equation Modeling (PLS-SEM) and survey data from 487 telecommunications customers in Saudi Arabia, the findings confirm significant positive direct effects for all four AI tools. Moreover, the VCE significantly amplifies these individual relationships and further strengthens their combined contribution to decision quality, enabling the model to explain 71.2% of the variance in purchasing decisions. The results indicate that competitive advantage in AI-enabled service markets depends not on deploying isolated technologies, but on orchestrating a coherent, high-quality virtual experience ecosystem. By integrating the Technology Acceptance Model (TAM) and Stimulus–Organism–Response (SOR) framework, this study advances the theoretical understanding of how AI and experience design jointly enhance digital decision-making. Practically, it underscores the need for managers to prioritize integrated VCE design to drive sustainable consumption and strengthen customer loyalty in increasingly digital service environments. Full article

This study analyses the educational and social impact of a series of innovative teaching projects developed at the Museum of the History of Pharmacy of the University of Seville. The initiatives—including historical video documentaries, the “student guides” programme, and the digital outreach project “Voices that Empower”—explore the pedagogical potential of scientific heritage as a learning tool and as a medium for public communication. Through experiential and service-learning methodologies, these projects have enhanced students’ communication skills, critical thinking, and awareness of cultural and gender dimensions within pharmaceutical studies. The results demonstrate that the integration of audiovisual production, museum-based learning, and digital storytelling fosters meaningful engagement between the university and society, while also revitalising the historical and humanistic dimensions of pharmacy. Furthermore, the inclusion of a gender perspective in the “Voices that Empower” initiative contributes to the visibility of women in STEM and highlights the museum as a space for empowerment and social transformation. This work concludes that university museums can act as strategic platforms for innovation in higher education, combining heritage preservation, teaching excellence, and civic outreach to promote a more inclusive and sustainable scientific culture. Full article

Artificial intelligence (AI) is transforming customer experience management (CXM) by enabling real-time, data-driven, and personalized interactions across digital touchpoints, including chatbots, voice assistants, generative AI, and immersive platforms. This study presents a PRISMA-based systematic literature review of 59 peer-reviewed studies published between 2021 and 2026, examining how AI-enabled personalization, privacy concerns, and customer value interact within AI-mediated customer experiences. Drawing on the Personalization–Privacy–Value (PPV) framework, the review synthesizes evidence on how AI-driven personalization enhances utilitarian, hedonic, experiential, relational, and emotional value, thereby strengthening satisfaction, engagement, loyalty, and behavioral intentions. At the same time, the findings reveal persistent tensions, as privacy concerns, perceived surveillance, algorithmic bias, and contextual moderators—including generational differences, cultural expectations, and technological literacy—frequently constrain value creation and erode trust. The review highlights that personalization benefits are highly contingent on transparency, perceived control, and ethical alignment, rather than personalization intensity alone. The study contributes by integrating ethical AI considerations into CXM research and clarifying conditions under which AI-enabled personalization leads to value creation versus value destruction. Managerially, the findings underscore the importance of ethical governance, transparent data practices, and customer-centered AI design to sustain trust and long-term customer relationships. Future research should prioritize longitudinal analyses of trust development, demographic heterogeneity, and cross-sector comparisons of AI governance as AI technologies become increasingly embedded in service ecosystems. Full article

Virtual assistants in academic environments often lack comprehensive multimodal integration and specialized role-based architecture. This paper presents NAIA (Nimble Artificial Intelligence Assistant), a robust artificial intelligence framework designed for multi-role virtual academic assistance through a modular monolithic approach. The system integrates Large Language Models (LLMs), Computer Vision, voice processing, and animated digital avatars within five specialized roles: researcher, receptionist, personal skills trainer, personal assistant, and university guide. NAIA’s architecture implements simultaneous voice, vision, and text processing through a three-model LLM system for optimized response quality, Redis-based conversation state management for context-aware interactions, and strategic third-party service integration with OpenAI, Backblaze B2, and SerpAPI. The framework seamlessly connects with the institutional ecosystem through Microsoft Graph API integration, while the frontend delivers immersive experiences via 3D avatar rendering using Ready Player Me and Mixamo. System effectiveness is evaluated through a comprehensive mixed-methods approach involving 30 participants from Universidad del Norte, employing Technology Acceptance Model (TAM2/TAM3) constructs and System Usability Scale (SUS) assessments. Results demonstrate strong user acceptance: 93.3% consider NAIA useful overall, 93.3% find it easy to use and learn, 100% intend to continue using and recommend it, and 90% report confident independent operation. Qualitative analysis reveals high satisfaction with role specialization, intuitive interface design, and institutional integration. The comparative analysis positions NAIA’s distinctive contributions through its synthesis of institutional knowledge integration with enhanced multimodal capabilities and specialized role architecture, establishing a comprehensive framework for intelligent human-AI interaction in modern educational environments. Full article

Background: This study reports on a community engagement knowledge-translation world café hosted in British Columbia, built on the research project “Enhancing cancer navigation for newly diagnosed, treated and post-treatment of people living with breast cancer in interior region”. The aim was to co-create a knowledge translation initiative with community stakeholders to enhance interdisciplinary approaches to psychosocial oncology. Methods: This study drew on implementation science and the consolidated framework for implementation research, which emphasize the importance of creating partnerships between researchers and engaging people for whom the research is meant to be of use—knowledge users and service users. Guided world café and purposeful sampling were used to engage a diverse range of stakeholders. Eighty stakeholders participated in this study from April 2023 to April 2024. Thematic analysis was conducted through familiarization, coding, theme development, review, definition, and reporting. Results: Eleven key themes emerged, including compassionate connection, time as a healing gift, empowering health literacy, informed compassion, holistic support ecosystem, empowering patient navigators, shared decision-making, empowering partnerships, digital–physical synergy, person-centered transformation, and accountability and collaboration. Conclusions: The key findings highlighted the need for continuous professional development for primary care providers, integrating patient-reported outcomes in electronic health records, leveraging digital health tools, and establishing community-engaged psychosocial oncology hubs to enhance care in rural communities. Recommendation: Recommendations include ongoing professional learning, embedding patient voices and lived experiences into care planning through digital tools, and empowering rural and diverse communities through inclusive and accessible cancer models of care. Full article

Since service robots serving as salespersons are expected to be deployed efficiently and sustainably in retail environments, this paper explores the impacts of their interaction cues on customer experiences within small-scale self-service shops. The corresponding customer experiences are discussed in terms of fluency, comfort and likability. We analyzed customers’ shopping behaviors and designed fourteen body gestures for the robots, giving them the ability to select appropriate movements for different stages in shopping. Two experimental scenarios with and without robots were designed. For the scenario involving robots, eight cases with distinct interaction cues were implemented. Participants were recruited to measure their experiences, and statistical methods including repeated-measures ANOVA, regression analysis, etc., were used to analyze the data. The results indicate that robots solely reliant on voice interaction are unable to significantly enhance the fluency, comfort and likability effects experienced by customers. Combining a robot’s voice with the ability to imitate a human salesperson’s body movements is a feasible way to truly improve these customer experiences, and a robot’s body movements can positively influence these customer experiences in human–robot interactions (HRIs) while the use of colored light cannot. We also compiled design strategies for robot interaction cues from the perspectives of cost and controllable design. Furthermore, the relationships between fluency, comfort and likability were discussed, thereby providing meaningful insights for HRIs aimed at enhancing customer experiences. Full article

Mobile networks have advanced significantly, providing high-throughput voice, video, and integrated data access to support connectivity through various services to facilitate high user density. This traffic growth has also increased the complexity of outlier detection (OD) for fraudster identification, fault detection, and protecting network infrastructure and its users against cybersecurity threats. Autoencoder (AE) models are widely used for outlier detection (OD) on unlabeled and temporal data; however, they rely on fixed anomaly thresholds and anomaly-free training data, which are both difficult to obtain in practice. This paper introduces statistical masking in the encoder to enhance learning from nearly normal data by flagging potential outliers. It also proposes a quasidynamic threshold mechanism that adapts to reconstruction errors, improving detection by up to 3% median area under the receiver operating characteristic (AUROC) compared to the standard 95% threshold used in base AE models. Extensive experiments on the Milan Human Telecommunications Interaction (HTA) dataset validate the performance of the proposed methods. Combined, these two techniques yield a 31% improvement in AUROC and a 34% lower computational complexity when compared to baseline AE, long short-term memory AE (LSTM-AE), and seasonal auto-regressive integrated moving average (SARIMA), enabling efficient OD in modern cellular networks. Full article

The rapid proliferation of generative artificial intelligence (GenAI) in educational settings has created unprecedented opportunities for language instruction, yet empirical evidence regarding its efficacy in primary-level English as a Foreign Language contexts remains scarce, particularly concerning pre-service teachers’ implementation experiences during formative practicum periods. This investigation, conducted in a public school in a non-Anglophone country during the Spring of 2025, examined the impact of GenAI-driven gamified activities on elementary pupils’ English language competencies while exploring novice educators’ professional development trajectories through a mixed-methods quasi-experimental approach with comparison groups. Four third-grade classes (n = 119 individuals aged 8–9) in a public school were assigned to either ChatGPT-mediated voice-interaction games (n = 58) or conventional non-digital activities (n = 61) across six 45 min lessons spanning three weeks, with four female student-teachers serving as instructors during their culminating practicum. Quantitative assessments of grammar, listening comprehension, and pronunciation occurred at baseline, post-intervention, and one-month follow-up intervals, while reflective journals captured instructors’ evolving perceptions. Linear mixed-effects modeling revealed differential outcomes across linguistic domains: pronunciation demonstrated substantial advantages for GenAI-assisted learners at both immediate and delayed assessments, listening comprehension showed moderate benefits with superior overall performance in the experimental condition, while grammar improvements remained statistically equivalent between groups. Thematic analysis uncovered pre-service teachers’ progression from technical preoccupations toward sophisticated pedagogical reconceptualization, identifying connectivity challenges and assessment complexities as primary barriers alongside reduced performance anxiety and individualized pacing as key facilitators. These findings suggest selective efficacy of GenAI across language skills while highlighting the transformative potential and implementation challenges inherent in technology-enhanced elementary language education. Full article

Integrated multidisciplinary care is recognised as essential for people living with motor neurone disease (PlwMND) and their families. The values underpinning integrated care, such as person-centredness, respect, empowerment, and co-production, are central to delivering meaningful and comprehensive support. Trust is an essential yet often overlooked element of effective person- and family-centred integrated care, particularly for PlwMND. While specialist multidisciplinary MND clinics represent the benchmark for evidence-based care, many PlwMND and their families depend significantly on local and community-based support services to maintain quality of life. Trust directly influences their engagement with these services and the continuity of care provided. Trust enables understanding of personal priorities and how they change as the disease progresses, ultimately allowing for person-centred care to happen. Trust is necessary to enable service co-production, which is a strong value of integrated care. Research highlights seven key domains of support essential to PlwMND and their carers: practical, social, informational, psychological, physical, emotional, and spiritual. Effective integrated care requires strong relationships built upon trust, shared decision-making, respect for individuality, and clear communication. Furthermore, due to the rapidly progressive nature of MND, care priorities and perceived symptom burdens may shift significantly over short periods, making flexible, temporally sensitive approaches critical. A dynamic, inclusive model of decision-making that fosters autonomy within and regular co-review of needs is recommended. This perspective paper examines how person- and family-centred integrated care is currently being delivered, what is working well, and how these practices can be further strengthened to enhance the care experiences of PlwMND, their families, and the health and social care providers involved. This paper builds on both theoretical knowledge and clinical experience to offer our perspective on the critical role of trust in co-producing integrated care for PlwMND. It brings together the voices of clinicians and researchers, alongside those with lived experience of MND. We propose a diagram of care that embeds the core values of integrated, person-centred care within the specific context of MND. Our aim is to enhance collaborative practices, strengthen cross-sector partnerships, and ultimately improve the care experiences for professionals, PlwMND, and their families. Full article

This study aimed to understand, through the voices of patients, the factors that contribute to inequality and inequity in oral healthcare and their implications for patient safety. A qualitative study was performed using a Grounded Theory approach (GT) through 13 in-depth interviews with a flexible design, recorded and transcribed verbatim for study purposes. Open and axial coding and analysis categories were generated, and a conceptual and explicative framework was established. Ethical approval was obtained. The main findings highlighted how individual, social, and contextual factors significantly influence the materialization of risks and failures in oral healthcare, ultimately affecting patient safety in dental practice. These factors include individual factors, the relationship between professionals and patients, and failures in healthcare service provision. Participants’ discourses showed examples of inequities, such as gender, socioeconomic gradient, educative level, type of healthcare system, discrimination, stigmatization, and othering-otherness, and their effect on dental care and dentistry safety. Health inequities should be tackled in a preventive and proactive manner through the effective integration of intersectoral policies and strategies. This approach would enhance oral health, make patient safety a fundamental pillar of dental care, uphold human dignity, and strengthen trust in the healthcare system. Full article

The growing need for secure and privacy-preserving identity management in industrial environments has exposed the limitations of traditional, centralized authentication systems. In this context, SIBERIA was developed as a modular solution that empowers users to control their own digital identities, while ensuring robust protection of critical services. The system is designed in alignment with European standards and regulations, including EBSI, eIDAS 2.0, and the GDPR. SIBERIA integrates a Self-Sovereign Identity (SSI) framework with a decentralized blockchain-based infrastructure for the issuance and verification of Verifiable Credentials (VCs). It incorporates multi-factor authentication by combining a voice biometric module, enhanced with spoofing-aware techniques to detect synthetic or replayed audio, and a behavioral biometrics module that provides continuous authentication by monitoring user interaction patterns. The system enables secure and user-centric identity management in industrial contexts, ensuring high resistance to impersonation and credential theft while maintaining regulatory compliance. SIBERIA demonstrates that it is possible to achieve both strong security and user autonomy in digital identity systems by leveraging decentralized technologies and advanced biometric verification methods. Full article

Automatic Speaker Verification (ASV) systems are increasingly employed to secure access to services and facilities. However, recent advances in speech deepfake generation pose serious threats to their reliability. Modern speech synthesis models can convincingly imitate a target speaker’s voice and generate realistic synthetic audio, potentially enabling unauthorized access through ASV systems. To counter these threats, forensic detectors have been developed to distinguish between real and fake speech. Although these models achieve strong performance, their deep learning nature makes them susceptible to adversarial attacks, i.e., carefully crafted, imperceptible perturbations in the audio signal that make the model unable to classify correctly. In this paper, we explore adversarial attacks targeting speech deepfake detectors. Specifically, we analyze the effectiveness of Basic Iterative Method (BIM) attacks applied in both time and frequency domains under white- and black-box conditions. Additionally, we propose an ensemble-based attack strategy designed to simultaneously target multiple detection models. This approach generates adversarial examples with balanced effectiveness across the ensemble, enhancing transferability to unseen models. Our experimental results show that, although crafting universally transferable attacks remains challenging, it is possible to fool state-of-the-art detectors using minimal, imperceptible perturbations, highlighting the need for more robust defenses in speech deepfake detection. Full article

Background: Internationally, digital health interventions have increasingly been adopted within hospital settings. Optimising their clinical implementation requires user involvement, but there is a lack of evidence regarding how this should be done. Objectives: This study was carried out to understand the acceptability and usability of a prototype Digital Antibiotic Review Tracking Toolkit and identify modifications required to optimise it ahead of a trial. Methods: The optimisation process involved online semi-structured interviews with a purposive sample of fifteen healthcare professionals recruited from Scotland and England, along with three service users, to gather feedback on the prototype’s design, content and delivery. Participants’ negative views were specifically sought to identify adaptations needed to ensure that the intervention’s components aligned optimally with end-user needs. Data were analysed using Framework Analysis guided by the RE-AIM implementation science framework (Reach, Effectiveness, Adoption, Implementation, and Maintenance) to identify key themes. Results: Participants mostly voiced positive views regarding the prototype, finding it acceptable, feasible and engaging. They also identified concerns relating to its adoption, system functionality, accessibility and maintenance that needed to be addressed. Anticipated low adoption rates were linked to issues surrounding computer literacy. This detailed user feedback informed rapid adjustments to the intervention to enhance its acceptability, perceived future credibility and usability in hospitals. Conclusions: This novel study illustrates how to identify, modify and adapt a digital intervention quickly and efficiently using qualitative iterative methods. Findings highlight the critical importance of contextualising end-user experience with health interventions to facilitate future engagement, uptake, and long-term use. This study also demonstrates how core elements of the MRC framework can be operationalised to help refine prototype digital interventions pre-trial. Full article