Automatic, camera-free lifelogging offers new opportunities for memory rehabilitation, personal informatics, and assistive technologies. However, most existing approaches limit daily activities to isolated event labels, offering little context and lacking the narrative coherence essential for effective lifelogging. Recent advances in audio–language models combine foundation audio processing with language-based reasoning, enabling open-ended sound understanding. We introduce EchoScriptor, an end-to-end system that transforms raw in-home audio into context-aware natural-language descriptions, generating coherent narrative lifelogs of activities and acoustic contexts. In moment-level evaluation, EchoScriptor achieved 94.15% activity recognition and 89.25% background recognition accuracy, and at the summary level, achieved an F1 score of 0.92, outperforming the classifier+LLM baseline. In our user study with 20 participants across 10 household activity videos, EchoScriptor summaries were consistently rated highly, approaching the perceived utility of human-written ones. By advancing from event detection to narrative understanding, EchoScriptor establishes a significant step toward automated, unobtrusive, context-aware lifelogging technologies.

This study introduces AutoCLC, an AI-powered system designed to assess and provide feedback on Closed-Loop Communication (CLC) in professional learning environments. CLC, where a sender’s Call-Out statement is acknowledged by the receiver’s Check-Back statement, is a critical safety protocol in high-reliability domains, including emergency medicine resuscitation teams. Existing methods for evaluating CLC lack quantifiable metrics and depend heavily on human observation. AutoCLC addresses these limitations by leveraging natural language processing and large language models to analyze audio recordings from Advanced Cardiovascular Life Support (ACLS) simulation training. The system identifies CLC instances, measures their frequency and rate per minute, and categorizes communications as effective, incomplete, or missed. Technical evaluations demonstrate that AutoCLC achieves 78.9% precision for identifying Call-Outs and 74.3% for Check-Backs, with a performance gap of only 5% compared to human annotations. A user study involving 11 cardiac arrest instructors across three training sites supported the need for automated CLC assessment. Instructors found AutoCLC reports valuable for quantifying CLC frequency and quality, as well as for providing actionable, example-based feedback. Participants rated AutoCLC highly, with a System Usability Scale score of 76.4%, reflecting above-average usability. This work represents a significant step toward developing scalable, data-driven feedback systems that enhance individual skills and team performance in high-reliability settings.