Sign up to save your podcasts
Or
Share The Challenge of Discoverability in Voice User Interfaces
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
The Challenge of Discoverability in Voice User Interfaces
In this episode of the Coo-ee Podcast, we are going to dive into a fascinating study on discoverability in voice user interfaces (VUI). We explore the paper "What Can I Say? Effects of Discoverability in VUIs on Task Performance and User Experience" by Kirschthaler, Porcheron, and Fischer, published at the 2nd Conference on Conversational User Interfaces.
The study examines two key strategies for helping users discover available voice commands: automatic prompts (where the system suggests commands) and user-initiated help (where users ask, "What can I say?"). Using a simulated food-ordering assistant called FeedMe, researchers tested these strategies to see their impact on task performance and usability. Their findings suggest that while automatic prompts lead to faster task completion and higher usability scores, user-initiated help is preferred for long-term use due to its non-intrusive nature.
Why does this matter? Unlike graphical interfaces, where menus and buttons provide clear guidance, VUIs are largely invisible, making command discoverability a significant challenge. This study underscores the importance of designing adaptable and intuitive systems that cater to both first-time and experienced users. We also discuss the ethical considerations of balancing efficiency with user autonomy.
📝 Link to the paper: https://doi.org/10.1145/3405755.3406119 👥 Authors: Philipp Kirschthaler, Martin Porcheron, Joel E. Fischer
Tune in to learn how these findings can shape the future of conversational AI and improve the usability of voice assistants!
🙋♂️ Find me on: halflingwizard.me
🎁 Support the Channel: If you’d like to support my work, check out my wishlist here: https://www.amazon.com/registries/gl/guest-view/1CD2D6CC95XGA. Your contributions support my content creation. Thank you!
#VoiceUserInterface #ConversationalAI #CUI #Discoverability #UserExperience #VoiceAssistant #TechResearch
View all episodes
By M. NamvarpourIn this episode of the Coo-ee Podcast, we are going to dive into a fascinating study on discoverability in voice user interfaces (VUI). We explore the paper "What Can I Say? Effects of Discoverability in VUIs on Task Performance and User Experience" by Kirschthaler, Porcheron, and Fischer, published at the 2nd Conference on Conversational User Interfaces.
The study examines two key strategies for helping users discover available voice commands: automatic prompts (where the system suggests commands) and user-initiated help (where users ask, "What can I say?"). Using a simulated food-ordering assistant called FeedMe, researchers tested these strategies to see their impact on task performance and usability. Their findings suggest that while automatic prompts lead to faster task completion and higher usability scores, user-initiated help is preferred for long-term use due to its non-intrusive nature.
Why does this matter? Unlike graphical interfaces, where menus and buttons provide clear guidance, VUIs are largely invisible, making command discoverability a significant challenge. This study underscores the importance of designing adaptable and intuitive systems that cater to both first-time and experienced users. We also discuss the ethical considerations of balancing efficiency with user autonomy.
📝 Link to the paper: https://doi.org/10.1145/3405755.3406119 👥 Authors: Philipp Kirschthaler, Martin Porcheron, Joel E. Fischer
Tune in to learn how these findings can shape the future of conversational AI and improve the usability of voice assistants!
🙋♂️ Find me on: halflingwizard.me
🎁 Support the Channel: If you’d like to support my work, check out my wishlist here: https://www.amazon.com/registries/gl/guest-view/1CD2D6CC95XGA. Your contributions support my content creation. Thank you!
#VoiceUserInterface #ConversationalAI #CUI #Discoverability #UserExperience #VoiceAssistant #TechResearch