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

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 tex...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-03
Main Authors: Lin, Susan, Warner, Jeremy, Zamfirescu-Pereira, J D, Lee, Matthew G, Jain, Sauhard, Huang, Michael Xuelin, Lertvittayakumjorn, Piyawat, Cai, Shanqing, Zhai, Shumin, Hartmann, Björn, Liu, Can
Format: Article
Language:English
Subjects:
Comparative studies
Graphical user interface
Revisions
Speech
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2401.10838