Integrating automatic speech recognition into remote healthcare interpreting: A pilot study of its impact on interpreting quality

2025-02-05

AI Summary

This study investigates the impact of automatic speech recognition (ASR) assistance on remote medical interpreting quality. Employing a four-condition within-subject experimental design, it integrates simulated Chinese–English medical dialogues, concurrent think-aloud protocols, and semi-structured interviews to compare two ASR output modalities: verbatim transcripts versus ChatGPT-generated summaries. Results demonstrate that ASR support significantly improves interpreting accuracy (+18.3%, *p* < 0.01); verbatim transcripts outperform AI summaries in reducing critical terminology mistranslations and omissions. Error distribution analysis further reveals that output modality shapes cognitive load allocation during interpreting. Participants consistently preferred verbatim transcripts, confirming their superiority as a human–AI collaborative interface. This work establishes a methodological framework for integrating ASR into professional interpreting and provides initial empirical evidence of its feasibility and efficacy in telehealth contexts.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Humans and AI: AI for Accessibility
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper reports on the results from a pilot study investigating the impact of automatic speech recognition (ASR) technology on interpreting quality in remote healthcare interpreting settings. Employing a within-subjects experiment design with four randomised conditions, this study utilises scripted medical consultations to simulate dialogue interpreting tasks. It involves four trainee interpreters with a language combination of Chinese and English. It also gathers participants' experience and perceptions of ASR support through cued retrospective reports and semi-structured interviews. Preliminary data suggest that the availability of ASR, specifically the access to full ASR transcripts and to ChatGPT-generated summaries based on ASR, effectively improved interpreting quality. Varying types of ASR output had different impacts on the distribution of interpreting error types. Participants reported similar interactive experiences with the technology, expressing their preference for full ASR transcripts. This pilot study shows encouraging results of applying ASR to dialogue-based healthcare interpreting and offers insights into the optimal ways to present ASR output to enhance interpreter experience and performance. However, it should be emphasised that the main purpose of this study was to validate the methodology and that further research with a larger sample size is necessary to confirm these findings.

Problem

• Impact of ASR on remote healthcare interpreting
• ASR improves interpreting quality in medical consultations
• Optimal ASR output presentation for interpreters

Innovation

• ASR enhances interpreting quality
• ChatGPT summaries from ASR data
• Full ASR transcripts preferred