Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation

TL;DR

Rambler is an LLM-powered interface that enhances speech-based writing by enabling gist-level manipulation and macro revisions, improving the efficiency and control of dictation editing.

Contribution

This work introduces Rambler, a novel GUI that integrates gist extraction and macro revision for speech-to-text editing, bridging the gap between spoken words and structured writing.

Findings

Rambler outperformed baseline in revision tasks.

Participants used diverse strategies effectively.

Enhanced user control improved editing efficiency.

Abstract

Dictation enables efficient text input on mobile devices. However, writing with speech can produce disfluent, wordy, and incoherent text and thus requires heavy post-processing. This paper presents Rambler, an LLM-powered graphical user interface that supports gist-level manipulation of dictated text with two main sets of functions: gist extraction and macro revision. Gist extraction generates keywords and summaries as anchors to support the review and interaction with spoken text. LLM-assisted macro revisions allow users to respeak, split, merge and transform dictated text without specifying precise editing locations. Together they pave the way for interactive dictation and revision that help close gaps between spontaneous spoken words and well-structured writing. In a comparative study with 12 participants performing verbal composition tasks, Rambler outperformed the baseline of a speech-to-text editor + ChatGPT, as it better facilitates iterative revisions with enhanced user control over the content while supporting surprisingly diverse user strategies.