Using Large Language Models to Accelerate Communication for Users with Severe Motor Impairments

TL;DR

This paper introduces SpeakFaster, a novel LLM-based interface that significantly reduces motor actions and accelerates text entry for users with severe motor impairments, demonstrated through simulations and user studies.

Contribution

The paper presents a new LLM-powered text entry system that saves motor actions and increases typing speed for AAC users, validated through offline simulations and real user testing.

Findings

57% more motor actions saved in offline simulation

29-60% faster text-entry rates in user studies

Effective phrase and word predictions from context-aware LLMs

Abstract

Finding ways to accelerate text input for individuals with profound motor impairments has been a long-standing area of research. Closing the speed gap for augmentative and alternative communication (AAC) devices such as eye-tracking keyboards is important for improving the quality of life for such individuals. Recent advances in neural networks of natural language pose new opportunities for re-thinking strategies and user interfaces for enhanced text-entry for AAC users. In this paper, we present SpeakFaster, consisting of large language models (LLMs) and a co-designed user interface for text entry in a highly-abbreviated form, allowing saving 57% more motor actions than traditional predictive keyboards in offline simulation. A pilot study with 19 non-AAC participants typing on a mobile device by hand demonstrated gains in motor savings in line with the offline simulation, while introducing relatively small effects on overall typing speed. Lab and field testing on two eye-gaze typing users with amyotrophic lateral sclerosis (ALS) demonstrated text-entry rates 29-60% faster than traditional baselines, due to significant saving of expensive keystrokes achieved through phrase and word predictions from context-aware LLMs. These findings provide a strong foundation for further exploration of substantially-accelerated text communication for motor-impaired users and demonstrate a direction for applying LLMs to text-based user interfaces.