From sight to insight: Unravelling student interpreters’ usage and perceptions of live captioning in Chinese–English simultaneous interpreting

Whereas computer-assisted interpreting (CAI) tools hold potential for simultaneous interpreting (SI), there is limited understanding of the way interpreters interact with and process live captioning during interpreting tasks. This study examined the interaction patterns and perceptions involved in live captioning among 27 student interpreters engaged in Chinese–English SI. Through a triangulated quantitative methodology incorporating eye-tracking data, temporal metrics, and participant feedback, we assessed the ways in which live captioning influences visual processing, temporal synchronization, and subjective experiences during SI tasks. The results reveal that student interpreters relied extensively on visual transcription during SI tasks. This heavy reliance on captioning appeared to affect their processing patterns, as evidenced by a gradually increasing ear–voice span (EVS) throughout sentence sequences. Whereas these interpreters generally viewed live captioning as a valuable CAI tool, their subjective feedback highlighted the need for customizable interfaces to accommodate individual processing styles and to optimize usability. These findings underscore the importance of integrating live captioning strategically into SI, together with targeted training to enhance interpreters’ use of tools and their attention management. This study contributes to ongoing research on CAI and SI, aligning itself with emerging perspectives on augmented interpreting that emphasize human–machine collaboration to enhance interpreter performance. It advocates a balanced evidence-based approach to incorporating such technologies into professional practice.