Exploring Interactions with Voice-Controlled TV
This work addresses the challenge of improving voice-controlled TV interfaces for users, but it is incremental as it builds on existing voice agent technology with a focus on recommendations.
The researchers tackled the problem of limited voice interactions on smart TVs by exploring a voice-only movie recommendation prototype, finding that users struggled with expressiveness versus efficiency and that designers need to mitigate voice-only drawbacks.
Intelligent agents such as Alexa, Siri, and Google Assistant are now built into streaming TV systems, allowing people to use voice input to navigate the increasingly complex set of apps available on a TV. However, these systems typically support a narrow range of control- and search-oriented commands, and do not support deeper recommendation or exploration queries. To learn about how people interact with a recommendation-oriented voice-controlled TV, we use research through design methods to explore an early prototype movie recommendation system where the only input modality is voice. We describe in-depth qualitative research sessions with 11 participants. We contribute implications for designers of voice-controlled TV: mitigating the drawbacks of voice-only interactions, navigating the tension between expressiveness and efficiency, and building voice-driven recommendation interfaces that facilitate exploration.