Numbers are an area of interpreting that is particularly prone to human error. Thanks to recent advancements in automatic speech recognition (ASR) and artificial intelligence (AI) technology, computer-assisted interpreting (CAI) tools may soon be used to enhance delivery accuracy for numbers during simultaneous interpreting (SI).

Given the novelty of the topic, the impact of in-booth CAI tool support on the SI of numbers is still largely under-researched. First, only a few studies have addressed the topic. Second, due to a number of methodological limitations, their findings yield only a partial understanding of the issue. The present work aims to make a theoretical and methodological contribution to this new area of inquiry. It identifies different research approaches to the interpretation of numbers. It then presents an empirical study on the computer-assisted SI of numbers with five Italian conference interpreters and the AI-powered CAI tool SmarTerp. The analysis contrasts two different research approaches and reveals the impact of speech design and evaluation methods on results. Implications and methodological recommendations for future studies are discussed.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.