Augmenting Music Listening Experiences on Voice Assistants

Voice interfaces have rapidly gained popularity, introducing the opportunity for new ways to explore new interaction paradigms for music. However, most interactions with music in current consumer voice devices are still relatively transactional; primarily allowing for keyword-based commands and basic content playback controls. They are less likely to contextualize content or support content discovery beyond what users think to ask for. We present an approach to dynamically augment the voice-based music experience with background information using story generation techniques. Our findings indicate that augmentation can have positive effects on voice-based music experiences, given the right user context and mindset