VoCa: Designing Speech-Canvas Interaction for Voice-Based Conversational Agents
Not on the map. Why?
Abstract (arXiv)
People write and sketch while speaking to explain, organize, and develop content together. Inspired by these practices, we investigate how voice agents can use a canvas alongside speech in multi-turn conversations with users. We conducted a two-part formative study: an observational study of how pairs coordinated speech and boardwork, followed by a design workshop that informed a design space for speech-canvas interaction with voice agents. Building on these insights, we developed VoCa, a voice agent that coordinates speech with visual object creation, annotation, and attention guidance. A five-day deployment with 18 participants examined usability, experiences of speech-canvas interaction, patterns of use, and desired improvements. Participants' experiences highlighted opportunities for speech-canvas interaction in learning, work, and daily life, alongside challenges in coordinating what agents say and show in ways users can follow and influence. These findings inform how voice agents can use a canvas alongside speech in conversation.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 82 references that are in the map. First posted on arXiv 3 Oct 2026.
Builds on
23 of 82 references.
References · 23
- 2024Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agentscited by 72
- 2023Graphologue: Exploring Large Language Model Responses with Interactive Diagramscited by 66
- 2023Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creationcited by 64
- 2024GazePointAR: A Context-Aware Multimodal Voice Assistant for Pronoun Disambiguation in Wearable Augmented Realitycited by 39
- 2024DynaVis: Dynamically Synthesized UI Widgets for Visualization Editingcited by 37
- 2025Generative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Modelcited by 26
- 2023User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistantscited by 15
- 2025Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agentscited by 15
- 2024GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learningcited by 14
- 2023Data Player: Automatic Generation of Data Videos with Narration-Animation Interplaycited by 13
- 2025Interactive Sketchpad: A Multimodal Tutoring System for Collaborative, Visual Problem-Solvingcited by 10
- 2023VOICE: Visual Oracle for Interaction, Conversation, and Explanationcited by 7
11 more
- 2024Cocobo: Exploring Large Language Models as the Engine for End-User Robot Programmingcited by 6
- 2024DrawTalking: Building Interactive Worlds by Sketching and Speakingcited by 5
- 2023Screen or No Screen? Lessons Learnt from a Real-World Deployment Study of Using Voice Assistants With and Without Touchscreen for Older Adultscited by 1
- 2025A Multimodal GUI Architecture for Interfacing with LLM-Based Conversational Assistantscited by 1
- 2025Proactive Agentic Whiteboards: Enhancing Diagrammatic Learningcited by 1
- 2026PointAloud: An Interaction Suite for AI-Supported Pointer-Centric Think-Aloud Computingcited by 1
- 2026What Are You Doing? Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processingcited by 1
- 2026Orality: A Semantic Canvas for Externalizing and Clarifying Thoughts with Speechcited by 1
- 2026Speech-Synchronized Whiteboard Generation via VLM-Driven Structured Drawing Representationscited by 1
- 2026When Drawing Is Not Enough: Exploring Spontaneous Speech with Sketch for Intent Alignment in Multimodal LLMscited by 1
- 2026Who's That Player?: Externalizing Query Interpretation in Spoken XR Sports Interactioncited by 1
Built on by
Not cited yet.