Learnability through Adaptive Discovery Tools in Voice User Interfaces

Furqan, Anushay; Myers, Chelsea M.; Zhu, Jichen

doi:10.1145/3027063.3053166

Cited by 46 publications

(25 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clearly communicating the affordances and limitations of a system is a longestablished design principle [61] and confirmed in human-AI interaction [6,19,26]. While the NN games do overall relatively well in communicating what the NN does (G1), they do not in communicating what it does not (G2).…”

Section: Learning Ai and Its Limitations Through Playmentioning

confidence: 99%

Player-AI Interaction: What Neural Network Games Reveal About AI as Play

Zhu

Villareale

Javvaji

et al. 2021

Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Learning Ai and Its Limitations Through Playmentioning

confidence: 99%

Player-AI Interaction: What Neural Network Games Reveal About AI as Play

Zhu

Villareale

Javvaji

et al. 2021

Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Given the general nature of this challenge, we referred to prior approaches in this space to identify design challenges and explore potential solutions. Specifically, we focus on adaptive NL command discovery interfaces that incrementally expose users to the system features through contextual suggestions (e.g., [16,28,44,58]), and explore how such suggestions can be generated during visual analysis. Query suggestions have also shown to benefit users during exploratory search tasks (e.g., [42,48]).…”

Section: User Interfaces For Natural Language Suggestionsmentioning

confidence: 99%

Snowy: Recommending Utterances for Conversational Visual Analysis

Srinivasan

Setlur

2021

The 34th Annual ACM Symposium on User Interface Software and Technology

View full text Add to dashboard Cite

Figure 1: Examples of utterance recommendations in Snowy. (A) To assist with the "cold start" problem during data analysis, Snowy infers potentially interesting patterns from the underlying dataset and suggests analytic inquiries one may want to begin exploring the data with. (B) Upon executing a NL utterance, Snowy suggests follow-up utterances to drill down into specific data subsets or adjust the current view. (C) As marks are selected on the view through direct manipulation, Snowy recommends deictic utterances to perform popular calculations using the selected marks.

show abstract

“…Many difficulties are a consequence of users' expectations of interacting with VUIs versus the reality of using existing commercial VUIs [18]. Learnability -learning how to use a VUI -is another pressing issue in current VUI design [13,26,46]. Schneiderman [36] highlighted key issues such as the cognitive effort required to interact with them, problems with presenting information through speech, and resolving errors due to speech recognition.…”

Section: Usability Of Voice Interfacesmentioning

confidence: 99%

“…Some researchers have explored the attitudes, perceptions, and experiences of VUI usability by current users [12,18,32]. Others have attempted to address VUI usability issues directly by working to develop solutions to specific VUI usability issues, such as creating tutorials and contextual help to improve learnability [11,13,46], and reducing the memory load required in VUI interaction [45]. Others have tried addressing VUI design more holistically, by developing design guidelines, heuristics, and methods for VUI systems [24,40,43].…”

Section: Improving Vui Interaction Designmentioning

confidence: 99%

Finding a New Voice: Transitioning Designers from GUI to VUI Design

Murad

Munteanu

Cowan³

et al. 2021

CUI 2021 - 3rd Conference on Conversational User Interfaces

View full text Add to dashboard Cite

As Voice User Interfaces (VUIs) become widely popular, designers must handle new usability challenges. However, compared to other established domains such as Graphical User Interfaces (GUIs), VUI designers have fewer resources (training support, usability heuristics, design patterns) to guide them. On the other hand, GUI-trained designers may also be solicited upon to design VUIs given the increased demand for such interfaces. This raises the question: how can we best support such designers as they transition from GUI to VUI design? To answer this, we focus on usability heuristics as a key resource, and conduct several workshops with GUI design experts, exploring how they map their design experience onto VUI design. Based on this, we suggest that the "path of least resistance" to transitioning designers from GUI to VUI may be the adaptation of familiar resources and concepts (such as GUI heuristics) to the VUI design space, instead of the imposition of novel VUI-specific heuristics on GUI-trained designers. This finding can inform the development of design resources that can support the increase demand for VUIs.

show abstract

Learnability through Adaptive Discovery Tools in Voice User Interfaces

Cited by 46 publications

References 8 publications

Player-AI Interaction: What Neural Network Games Reveal About AI as Play

Player-AI Interaction: What Neural Network Games Reveal About AI as Play

Snowy: Recommending Utterances for Conversational Visual Analysis

Finding a New Voice: Transitioning Designers from GUI to VUI Design

Contact Info

Product

Resources

About