Towards Age-friendly E-commerce Through Crowd-Improved Speech Recognition, Multimodal Search, and Personalized Speech Feedback

This paper presents an age-friendly system for improving the elderly's online shopping experience. Different from most related studies focusing on website design and content organization, we propose to integrate three assistive techniques to facilitate the elderly's browsing of products in E-commerce platforms, including the crowd-improved speech recognition, the multimodal search, and the personalized speech feedback. The first two techniques, namely, the crowd-improved speech recognition and the multimodal search, work together to allow the elderly search for desired products flexibly using either speech, an image, text, or any combination of them whichever are convenient for the elderly. The personalized speech feedback provides a speech summary of search result in a personalized voice. That is, the elderly are allowed to choose or even create their desired voices, and also can customize the voices in terms of pitch, speaking speed, and loudness. As a whole, the proposed system is expected to help and engage the elderly's E-commerce adoption. Testing on real-world E-commerce product datasets demonstrated the usability of the proposed system.