Designing Inclusive Voice Assistants: Breaking Stereotypes with Q

Designing the Right Robot Voice: Aligning Sound with Personality

In this episode of the Coo-ee Podcast, we explore the fascinating world of robot voice design and its impact on user experience. Imagine purchasing a friendly-looking social robot, only to be met with a cold, mechanical voice that feels completely out of place. This disconnect can lead to frustration and hinder meaningful interactions. So, how can designers ensure that a robot’s voice aligns with its appearance and function? We discuss the research paper The Right Kind of Unnatural: Designing a Robot Voice by Matthew P. Aylett, Selina Jeanne Sutton, and Yolanda Vazquez-Alvarez, presented at the 1st International Conference on Conversational User Interfaces. This study delves into the challenges of crafting robot voices that enhance usability and personality while maintaining coherence with a robot’s design. The paper explores how advanced synthetic voices, like Google Duplex, raise concerns about appropriateness in robotic design. It examines case studies of robots like Haru, Jibo, and Vector, which illustrate the importance of aligning voice with character. The research provides practical design principles to ensure robot voices feel engaging, natural, and functional. It also highlights the role of parametric synthesis and contextual awareness in making robot interactions more seamless and personalized. Ethical considerations in voice diversity and inclusivity are also discussed. Why does this matter? Social robots are increasingly becoming part of our daily lives, and their voices play a crucial role in shaping user experience. Mismatched voices can create confusion and frustration, reducing the effectiveness of these technologies. By integrating thoughtful voice design from the outset, developers can create robots that feel intuitive and enjoyable to interact with. 📝 Link to the paper: https://doi.org/10.1145/3342775.3342806 [https://doi.org/10.1145/3342775.3342806]  👥 Authors: Matthew P. Aylett, Selina Jeanne Sutton, Yolanda Vazquez-Alvarez Tune in to learn how these insights can shape the future of Conversational User Interfaces and improve the design of social robots! 🙋‍♂️ Find me on: halflingwizard.me [https://halflingwizard.me/]  🎁 Support the Channel: If you’d like to support my work, check out my wishlist here: Amazon Wishlist [https://www.amazon.com/registries/gl/guest-view/1CD2D6CC95XGA]. Your contributions support my content creation. Thank you! #ConversationalUI #RobotDesign #VoiceTechnology #HumanRobotInteraction #SocialRobots #TechResearch

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 [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 [https://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 [https://www.amazon.com/registries/gl/guest-view/1CD2D6CC95XGA]. Your contributions support my content creation. Thank you! #VoiceUserInterface #ConversationalAI #CUI #Discoverability #UserExperience #VoiceAssistant #TechResearch

When Should Smart Speakers Speak Up? Exploring Proactive AI in Conversations

In this episode of the Coo-ee Podcast, we dive into the research study May I Interrupt? Diverging Opinions on Proactive Smart Speakers, presented at the 3rd Conference on Conversational User Interfaces. This study examines how people feel about smart speakers that go beyond responding to commands and proactively initiate conversations. Through an online survey with 47 participants, researchers explored user reactions to eight different proactive interaction scenarios featuring a fictional assistant named “Jay.” The findings reveal that while proactive AI can be helpful, timing, context, and tone significantly impact user acceptance. Some interactions—like reminders about important events—were welcomed, while others—like unsolicited health suggestions—felt intrusive. This study laid the groundwork for a follow-up research paper discussed in episode 4, which refined strategies for making proactive AI assistants more socially aware. In this episode, we compare insights from both studies, highlighting key design principles that can make AI interactions feel more natural and user-friendly. 📝 Link to the paper: https://doi.org/10.1145/3469595.3469629 [https://doi.org/10.1145/3469595.3469629] 👥 Authors: Leon Reicherts, Nima Zargham, Michael Bonfert, Yvonne Rogers, Rainer Malaka 🙋‍♂️ Find me on: https://halflingwizard.me [https://halflingwizard.me/] 🎁 Support the Channel: If you’d like to support our work, check out our wishlist here: https://www.amazon.com/registries/gl/guest-view/1CD2D6CC95XGA [https://www.amazon.com/registries/gl/guest-view/1CD2D6CC95XGA] Your contributions support our content creation. Thank you!

Designing Inclusive Voice Assistants: Breaking Stereotypes with Q

In this episode of the Coo-ee Podcast, we explore the groundbreaking study Eschewing Gender Stereotypes in Voice Assistants to Promote Inclusion by Andreea Danielescu. Published at the 2nd Conference on Conversational User Interfaces, this research dives into the social implications of voice assistant design, from reinforcing gender stereotypes to excluding non-binary individuals and marginalized groups. The episode highlights the development of Q, a genderless voice assistant created to foster inclusivity by sitting between traditional male and female vocal ranges. We discuss how Q was crafted, the cultural and technical challenges of designing such a voice, and the biases present in speech recognition systems. This study reveals the potential for voice technology to drive social change, emphasizing the importance of thoughtful design in creating equitable, inclusive tools for diverse users. 📝 Link to the paper: https://doi.org/10.1145/3405755.3406151 [https://doi.org/10.1145/3405755.3406151] 👥 Author: Andreea Danielescu 🙋‍♂️ Find me on: halflingwizard.me [https://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 [https://www.amazon.com/registries/gl/guest-view/1CD2D6CC95XGA]. Your contributions support my content creation. Thank you! #Inclusion #VoiceAssistants #GenderNeutralDesign #ConversationalAI #CUI

Accents Matter: How Virtual Assistants Shape Our Words

In this episode of the Coo-ee Podcast, we dive into the fascinating study, “What’s in an Accent? The Impact of Accented Synthetic Speech on Lexical Choice in Human-Machine Dialogue” by Benjamin R. Cowan, Philip Doyle, Justin Edwards, Diego Garaialde, Ali Hayes-Brady, Holly P. Branigan, João Cabral, and Leigh Clark. The study reveals how the accent of virtual assistants influences our word choices during interactions. From “jumper” vs. “sweater” to how partner models guide our communication, this research sheds light on the subtle dynamics of language adaptation in human-machine dialogue. We also explore the implications for designing conversational systems that are inclusive, natural, and culturally aware. Tune in to learn how accents play a crucial role in breaking communication barriers. 📝 Link to the paper: https://doi.org/10.1145/3342775.3342786 [https://doi.org/10.1145/3342775.3342786] 👥 Authors: Benjamin R. Cowan, Philip Doyle, Justin Edwards, Diego Garaialde, Ali Hayes-Brady, Holly P. Branigan, João Cabral, Leigh Clark 🙋‍♂️ Find me on: halflingwizard.me [https://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 [https://www.amazon.com/registries/gl/guest-view/1CD2D6CC95XGA] Your contributions support my content creation. Thank you! #Hashtags: #ConversationalUI #VirtualAssistants #AccentsInTech #HCI #LanguageAdaptation