Contemporary smart home speakers (Amazon Echo™, Google Nest™) represent an opportunity to capture streams of big data that represent user interactions. Once captured, these data streams may be analyzed to understand use patterns for different demographics. In this research, we focus on one demographic, the aging-at-home elderly. We describe how such data streams may be captured with appropriate safeguards from smart home speakers deployed in the homes of the elderly individuals. We analyze the data to develop visual representations and sonifications to discover several patterns about aggregate use, use intensity, use progression over time, and types of use. Based on these, we draw tentative conclusions about the aging-at-home elderly make use of smart speakers at home, identify some problems, and describe how the empirical findings may be used to discover new voice skills that can contribute to the quality of life for the elderly. The paper concludes with a discussion of possibilities for applying the approach we have demonstrated for larger data sets.

当代的智能家居扬声器（Amazon Echo™，Google Nest™）为捕获代表用户互动的大数据流提供了机会。捕获后，可以对这些数据流进行分析，以了解不同人口统计学的使用模式。在这项研究中，我们关注的是一个人口统计学家中的老年人。我们描述了如何使用部署在老年人房屋中的智能家居扬声器通过适当的防护措施捕获此类数据流。我们分析数据以开发可视化表示法和超声波显示法，以发现有关总体使用，使用强度，随着时间推移的使用进展以及使用类型的几种模式。在此基础上，我们得出了关于老年人在家中使用智能扬声器的初步结论，确定了一些问题，并描述经验发现可如何用于发现可以提高老年人生活质量的新语音技能。本文最后讨论了应用我们针对较大数据集展示的方法的可能性。