The general objective of the ANTRACT project is the analysis of the images and sounds produced weekly in the framework of an independent company created in 1945, les Actualités françaises (French News), over twenty five years. This major cinematographic vector, already partially worked, has never been the subject of a systematic analysis. Thanks to recent technological tools for the analysis of textual and audiovisual contents, image, video and sound analysis, automatic speech transcription and textometry in particular, the aim is to provide the scientific community with new analysis frameworks.
Technological, historical, methodological and heritage issues are identified. The technological challenge lies in the improvement of the analysis technologies of speech and image modalities, in the joint exploitation of available modalities (image, text and speech) for qualitative and
quantitative analysis, and in the specification and implementation of tools adapted to the documents treated and to the uses prescribed by the historical analysis of this corpus. The historical issue is divided into four orientations: 1) the evolution of France in its colonial, economic, social, political, cultural and international dimension; 2) the way in which media representations and social facts are articulated; 3) the memorial dimension and 4) the construction of an audiovisual history. The methodological challenge lies in the implementation of a coherent and comprehensive methodological approach and is the general objective of the project. The heritage issue lies in the importance of this corpus which the project proposes to enrich and make available to researchers and general public.
The project presents both fundamental research dimensions for historical research and for its transdisciplinary approach, as well as the dimensions of experimental development for technological work, which largely involves adapting the tools of the partners to the uses and the data of the project. The choice is made to deposit it as an experimental development project.
The project is coordinated by Pascale Goetschel, Director of the Center for Social History of the 20th Century (Paris 1). The consortium brings together academic, industrial and institutional partners, specialized and recognized in the fields of history, textometry, image and video analysis, speech processing and audiovisual archives management. The project is organized according to a principle that underpins the transdisciplinary aspect of the project. Sub-project 1 is reserved for the coordination of the project. Sub-project 2 groups together tasks related to corpus gathering, data management and technological research. Sub-project 3 is the main place for methodological and transdisciplinary reflection, following an iterative principle of successive phases of expressions of needs, experiments and feedback. Sub-project 4 regroups the tasks that produce the project's actual results in terms of science, technology, industry and heritage.
At the end of the project, the results will be made available as widely as possible. The corpus enriched with data and metadata will be made available to the scientific and technological community. The software modules will be offered in open source whenever possible and a web portal will be opened. In addition, the Voxolab company will integrate the results of research carried out in speech transcription.
Madame Pascale GOETSCHEL (Centre d'histoire sociale du XXe siècle)
The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.
LIUM LABORATOIRE D'INFORMATIQUE DE L'UNIVERSITE DU MAINE (LIUM)
IHRIM Institut d'Histoire des Représentations et des Idées dans les Modernités
INA Institut national de l'audiovisuel
CHS Centre d'histoire sociale du XXe siècle
Help of the ANR 565,946 euros
Beginning and duration of the scientific project: November 2017 - 36 Months