Hybrid workflows for real-time interlingual communication via speech recognition. The SMART project

Technologies are changing the landscape of translation and interpreting, leading to the development of hybrid workflows to cope with the increasing demand for multilingual audiovisual content to be made accessible as quickly as possible and across sensory and language barriers. In relation to spoken interlingual communication in real time, speech recognition and machine translation are opening up new translational practices to achieve this goal, which are characterised by different degrees of human-machine interaction and can be placed on a continuum from human-centric to human-in-the-loop and automated ones. This talk focuses on interlingual respeaking as a the most human-centric practice for live interlingual subtitling. Interlingual respeaking is a speech recognition-based method that relies on human-machine interaction, where the human listens to live input and simultaneously translates it into a target language (with added oral punctuation) to speech recognition software that turns it into written text displayed on a screen (Pöchhacker and Remael 2020, Romero-Fresco and Pöchhacker 2017). As a form of ‘simultaneous interpreting 2.0‘, it relies on advanced cognitive abilities, interpersonal traits and procedural skills across various domains (Davitti and Sandrelli 2020; Sandrelli 2020). Based on findings from the SMART project (Shaping Multilingual Access through Respeaking Technology), a project funded by the Economic and Social Research Council UK (ES/ T002530/1, 2020-2022), this presentation will discuss the multifactorial and multimethod designed to explore the human variables (procedural, cognitive, interpersonal) involved in this complex practice. Data was collected from an experiment involving over 50 language professionals from (a combination of) relevant backgrounds in interpreting/translation/ subtitling/intralingual respeaking and working into six language directions (English <> Italian, French, Spanish). Emphasis will be placed on the interdisciplinarity of the approach adopted, which is informed by the expertise of leading experts on respeaking and interpreting and psychologists offering important cognitive insights into the intricacies of the process through triangulation of quantitative and qualitative data. Instead of using technological determinism as a starting point to study human-machine interaction, the study uses human performance as a starting point to gain increased awareness of the challenges involved in the process and skillset necessary to perform interlingual respeaking, thus ultimately feeding into the broader debate on responsible human-machine interaction.