Finding contextual meaning of the wake word

Abstract

The 'wake word' can be considered one of the features that hinder natural conversation. Recently, tech companies such as Google and Amazon have developed features that enable the user to communicate with the virtual agent without a wake word. With this type of feature, conversation with a voice agent could be more natural, like Human-Human Conversation (HHC). However, the elimination of the wake word in a Voice User Interface (VUI) should be considered carefully, as it is perceived by users not only as technical feature, but also as a contextual feature. In this paper, we conducted a preliminary user study to understand how people use a wake word while interacting with their voice agent. We found out that users felt that they took control of the conversation with the voice agent by using the wake word. Furthermore, they tended to project negative feeling onto the wake word, because they usually convey negative with the wake word (e.g., to reset a failed conversation). Based on these findings, we discuss the contextual meaning of the wake word from the perspective of VUI design.