Evaluating a Multi-Agent Voice-Enabled Smart Speaker for Care Homes: A Safety-Focused Framework

📅 2026-03-24
📈 Citations: 0
Influential: 0
📄 PDF
📝 Abstract
Artificial intelligence (AI) is increasingly being explored in health and social care to reduce administrative workload and allow staff to spend more time on patient care. This paper evaluates a voice-enabled Care Home Smart Speaker designed to support everyday activities in residential care homes, including spoken access to resident records, reminders, and scheduling tasks. A safety-focused evaluation framework is presented that examines the system end-to-end, combining Whisper-based speech recognition with retrieval-augmented generation (RAG) approaches (hybrid, sparse, and dense). Using supervised care-home trials and controlled testing, we evaluated 330 spoken transcripts across 11 care categories, including 184 reminder-containing interactions. These evaluations focus on (i) correct identification of residents and care categories, (ii) reminder recognition and extraction, and (iii) end-to-end scheduling correctness under uncertainty (including safe deferral/clarification). Given the safety-critical nature of care homes, particular attention is also paid to reliability in noisy environments and across diverse accents, supported by confidence scoring, clarification prompts, and human-in-the-loop oversight. In the best-performing configuration (GPT-5.2), resident ID and care category matching reached 100% (95% CI: 98.86-100), while reminder recognition reached 89.09\% (95% CI: 83.81-92.80) with zero missed reminders (100% recall) but some false positives. End-to-end scheduling via calendar integration achieved 84.65% exact reminder-count agreement (95% CI: 78.00-89.56), indicating remaining edge cases in converting informal spoken instructions into actionable events. The findings suggest that voice-enabled systems, when carefully evaluated and appropriately safeguarded, can support accurate documentation, effective task management, and trustworthy use of AI in care home settings.
Problem

Research questions and friction points this paper is trying to address.

voice-enabled smart speaker
care homes
safety evaluation
speech recognition
reminder extraction
Innovation

Methods, ideas, or system contributions that make the work stand out.

safety-focused evaluation
retrieval-augmented generation (RAG)
voice-enabled smart speaker
human-in-the-loop
care home AI
Z
Zeinab Dehghani
University of Hull, UK
R
Rameez Raja Kureshi
University of Hull, UK
Koorosh Aslansefat
Koorosh Aslansefat
Assistant Professor of Computer Science, University of Hull
Reliability and SafetyAI SafetyTrustworthy AIExplainable AI
F
Faezeh Alsadat Abedi
University of Southampton, UK
D
Dhavalkumar Thakker
University of Hull, UK
L
Lisa Greaves
Connexin, Hull, UK
B
Bhupesh Kumar Mishra
University of Hull, UK
B
Baseer Ahmad
University of Hull, UK
T
Tanaya Maslekar
Leeds Teaching Hospital NHS Trust, UK