Abstract
Remote simultaneous interpreting (RSI) draws on Information and Communication Technologies (ICTs) to facilitate multilingual communication by connecting conference interpreters to in-presence, virtual or hybrid events. Early solutions for RSI involved interpreters working in interpreting booths with physical hardware. However, in recent years, cloud-based solutions for RSI have emerged, with innovative Simultaneous Interpreting Delivery Platforms (SIDPs) at their core, enabling RSI delivery from anywhere. Initial explorations of the cloud-based solutions suggest that there is room for improving many of the widely used SIDPs. This paper outlines an ongoing experimental study that investigates two aspects of SIDPs: the design of the interpreter interface and the integration of automatic speech recognition (ASR) in the interface to aid/augment the interpreter's source-text comprehension. Preliminary pilot study data suggests interpreters have a preference towards cleaner interfaces with better view of the speaker's hand gestures and body language. Performance analysis of a subsample of three participants indicates that while the most experienced interpreter had a similar performance across different experimental conditions (i.e., presentation of source speech with/without ASR-generated transcript), differences were apparent for the other two interpreters. KEYWORDS remote simultaneous interpretation (RSI), simultaneous interpreting delivery platforms (SIDPs), presence, user experience, automatic speech recognition (ASR)