This project focuses on the influence of neural machine translation on audio description (AD). It has become a relevant topic, because recent EU legislation calls for an increased supply of AD in films and series. In order to meet this demand, it is important to investigate how the implementation of machine translation in the creation process of AD could be a solution. However, AD has its own translation problems. That is why this research is based on the following questions:
The research is a mixed-methods study. This means that it consists of an experiment with professional audio describers, but also a text analysis and thorough, interdisciplinary study of the literature. In this way, the findings are linked to the latest developments in research into machine translation. The project constitutes a first step to gather fundamental knowledge regarding the study of technology for multimodal text types and strategic knowledge to start developing machine translation for audio description more systematically.