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 

👥 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 

🎁 Support the Channel: If you’d like to support my work, check out my wishlist here: Amazon Wishlist.

Your contributions support my content creation. Thank you!

#ConversationalUI #RobotDesign #VoiceTechnology #HumanRobotInteraction #SocialRobots #TechResearch

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

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

👥 Authors: Leon Reicherts, Nima Zargham, Michael Bonfert, Yvonne Rogers, Rainer Malaka

🙋‍♂️ Find me on: 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

Your contributions support our content creation. Thank you!

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

👥 Author: Andreea Danielescu

🙋‍♂️ 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!

#Inclusion #VoiceAssistants #GenderNeutralDesign #ConversationalAI #CUI

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

👥 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

🎁 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!

#Hashtags: #ConversationalUI #VirtualAssistants #AccentsInTech #HCI #LanguageAdaptation

This episode of the Coo-ee Podcast dives into the complexities of gender perception in voice user interfaces (VUIs), exploring Selina Jeanne Sutton’s paper, Gender Ambiguous, Not Genderless: Designing Gender in Voice User Interfaces with Sensitivity. Sutton critiques the idea of “genderless” voices and advocates for “gender ambiguous” designs that challenge societal biases and promote inclusivity. From the pitch and tone of voices to device branding and task assignments, this study highlights how every design choice influences user perceptions. By addressing these nuances, designers can create tools that respect diverse gender identities and move beyond binary categorizations.

Tune in as we unpack how smart assistant designs often inadvertently reinforce stereotypes and how thoughtful, holistic approaches can foster a more inclusive user experience.

👥 Author: Selina Jeanne Sutton

📝 Link to the paper: https://doi.org/10.1145/3405755.3406123

🙋‍♂️ 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!

#VoiceAssistants #GenderAmbiguity #InclusiveDesign #VUIs #TechnologyDesign

In this episode of the Coo-ee Podcast, we dive into the fascinating world of Conversational User Interfaces through the lens of a study titled “The User Experience of ChatGPT: Findings from a Questionnaire Study of Early Users” by Marita Skjuve, Asbjørn Følstad, and Petter Bae Brandtzaeg. Presented at the 5th International Conference on Conversational User Interfaces, this research sheds light on how early adopters perceived ChatGPT, balancing its practical benefits with its creative and engaging capabilities.

We explore the study’s methodology, including feedback from 194 participants who shared their experiences with ChatGPT, ranging from its ability to simplify complex topics and inspire creativity to frustrations stemming from inaccuracies and irrelevant answers. Using a pragmatic-hedonic framework, the researchers unpacked the dual nature of user experiences, offering actionable recommendations for designing reliable, enjoyable conversational AI tools.

Join us as we discuss the implications for education, professional tasks, and beyond, emphasizing the importance of trust, precision, and human-like interaction in conversational AI design.

📝 Link to the paper: https://doi.org/10.1145/3571884.3597144

👥 Authors: Marita Skjuve, Asbjørn Følstad, Petter Bae Brandtzaeg

🙋‍♂️ 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!

In this episode of the Coo-ee Podcast, we delve into a thought-provoking study titled “I Don’t Know What You’re Talking About, HALexa: The Case for Voice User Interface Guidelines” by Christine Murad and Cosmin Munteanu. Published at the 1st International Conference on Conversational User Interfaces, this paper tackles the usability issues that plague voice interfaces like Alexa and Google Home. From misunderstood commands to vague feedback, these challenges often frustrate users—especially older adults—highlighting the need for better design principles.

The authors propose a framework of tailored guidelines for Voice User Interfaces (VUIs) to bridge the gap between user expectations and real-world functionality. Through actionable insights, the paper addresses error handling, conversational context, and inclusivity, laying the groundwork for a taxonomy that can shape the future of intuitive and accessible VUIs. We’ll explore their findings, the steps they recommend for developers, and how these principles could turn frustrating interactions into seamless experiences.

📝 Link to the paper: https://doi.org/10.1145/3342775.3342795

👥 Authors: Christine Murad, Cosmin Munteanu

🙋‍♂️ 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!

#Hashtags: #VoiceInterfaces #UXDesign #TechForAll #HumanComputerInteraction #ConversationalUI

In this episode of the Coo-ee Podcast, we dive into the study “Understanding Circumstances for Desirable Proactive Behaviour of Voice Assistants: The Proactivity Dilemma” by Nima Zargham, Leon Reicherts, Michael Bonfert, Sarah Theres Voelkel, Johannes Schoening, Rainer Malaka, and Yvonne Rogers. Published in the Proceedings of the 4th Conference on Conversational User Interfaces, the study explores how proactive voice assistants can offer support while avoiding intrusiveness, particularly in social and domestic settings. Through storyboards and interviews with participants, the researchers highlight the importance of context-awareness, user control, and sensitivity to social dynamics when designing these technologies.

The findings emphasize a balance between usefulness and privacy, suggesting that proactive assistants should adapt to the environment, provide customizable features, and communicate in ways that align with users’ preferences. For example, sending private alerts instead of public notifications can help avoid embarrassing situations in shared spaces. These insights provide valuable guidance for creating voice assistants that enhance user experience while respecting autonomy and trust.

📝 Link to the paper: https://doi.org/10.1145/3543829.3543834

👥 Authors: Nima Zargham, Leon Reicherts, Michael Bonfert, Sarah Theres Voelkel, Johannes Schoening, Rainer Malaka, and Yvonne Rogers

🙋‍♂️ 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!

Hashtags: #VoiceAssistants #ProactiveAI #UserExperience #AIPrivacy #CooeePodcast

In this episode of the Coo-ee Podcast, we delve into the fascinating world of conversational user interfaces (CUIs) and explore the challenges of creating seamless voice interactions. Using the paper Progressivity for Voice Interface Design by Fischer et al. as our guide, we uncover why conversations with voice assistants often falter and how progressivity can help keep interactions on track.

Through real-world data from Amazon Echo users, the study highlights the importance of maintaining dialogue flow, offering actionable insights for designers and developers. From addressing non-preferred responses to prioritizing concise, context-aware prompts, this research redefines what effective voice interface design should look like. Whether you’re a developer, UX designer, or simply curious about the future of conversational technology, this episode offers a fresh perspective on improving voice assistant interactions.

📝 Link to the paper: https://doi.org/10.1145/3342775.3342788

👥 Authors: Joel E. Fischer, Stuart Reeves, Martin Porcheron, Rein Ove Sikveland

🙋‍♂️ 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!

#VoiceInterfaces #UserExperience #CUI #DesignThinking #HumanComputerInteraction #TechInnovation