TADS: Translation of Audio Description Scripts
Description of the project (starting in January 2021, if funding provided)
Audio description (AD) is a technique that allows people with visual impairments to obtain the information needed to follow the action of an audiovisual product (e.g. a TV movie). Research on this technique is part of the field of traductology, which deals with inter-semiotic forms of translation. In the case of television series or films dubbed or subtitled for the international market, the production of AD scripts goes hand in hand with translation tasks. The question then arises whether it is better to translate (parts of) an AD script semi-automatically or whether it is better to write a new one directly in the target language of the film. Our project aims to study this question with the help of a digital corpus containing AD scripts of TV series and feature films in French and German (either original versions and their translations or comparable film genres). Created for the project and annotated by the research team, this corpus will make it possible to do contrastive analysis of the characteristics of a large number of AD scripts.
Experimental studies will be carried out before and after the corpus tasks in order to evaluate the effects of different methods of creating AD scripts on the selection of elements of the images to be described, on the coherence of the text and, towards the end of the project, on the comprehension and acceptance of the translations by the target audience. The objective of the corpus analysis and experimental studies is to identify differences in the process of describing moving images. The results of the analyses will provide data that can be used in a future project as training material for translators working on a neural model and can advance the field of image recognition.
Main team members (alphabetical order):
|First name||Last name||University|
|Céline||Largier Vié||Université Paris 3 Sorbonne Nouvelle|
|Saskia Josephine||Schulz||Universität Hildesheim|
Working Group Meeting
On November 19th 2020, the first meeting of the TADS-group took place. Due to the current situation the meeting was held on Zoom.
The following members attended the meeting:
University of Hildesheim:
Kooperation mit "Video to Voice" im TADS-Projekt und in der Lehre
VIDEO TO VOICE develops tools that make audiovisual content accessible to all, regardless of disability. The Berlin-based firm’s software incorporates machine translation technology, allowing audio descriptions to be produced in over 40 languages.
We would like to thank "Video to Voice" for granting us free access to their platform.
Find more information on: https://www.videotovoice.com