Orality: A Semantic Canvas for Externalizing and Clarifying Thoughts with Speech

2026-03-02

AI Summary

This work addresses the challenges posed by the inherent disfluencies, repetitions, and disorganization of spoken language, which often impede clear thinking. To tackle this, the authors propose Orality, a system that leverages automatic speech recognition to extract key content and employs large language models for semantic analysis, generating an interactive node-link graph. This graph enables users to visually structure their thoughts and dynamically reorganize content through voice commands. The study pioneers the integration of externalized oral thought with semantic graph representations, establishing a dual-modality framework—graphical and conversational—for thought clarification. It further introduces AI-generated probing questions and logical inconsistency detection. User studies demonstrate that Orality significantly outperforms using ChatGPT alone for voice-based interaction in supporting users to clarify and develop their ideas, highlighting the unique advantages of graphical thinking tools.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Speech
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

People speak aloud to externalize thoughts as one way to help clarify and organize them. Although Speech-to-text can capture these thoughts, transcripts can be difficult to read and make sense due to disfluencies, repetitions and potential disorganization. To support thinking through verbalization, we introduce Orality, which extracts key information from spoken content, performs semantic analysis through LLMs to form a node-link diagram in an interactive canvas. Instead of reading and working with transcripts, users could manipulate clusters of nodes and give verbal instructions to re-extract and organize the content in other ways. It also provides AI-generated inspirational questions and detection of logical conflicts. We conducted a lab study with twelve participants comparing Orality against speech interaction with ChatGPT. We found that Orality can better support users in clarifying and developing their thoughts. The findings also identified the affordances of both graphical and conversational thought clarification tools and derived design implications.

Problem

• orality
• thought clarification
• speech-to-text
• semantic analysis
• externalization

Innovation

• Orality
• semantic analysis
• node-link diagram
• thought clarification
• speech interaction