Powerful language technology tools and methods to support oral history research Presentation by Josef Fruehwald of the University of Edinburgh at the event "Exploring Spoken Word Data in Oral History Archives", held at the e-Research Centre, University of Oxford on 18-19 April 2016, organized by Martin Wynne as part of the CLARIN-PLUS project (http://www.clarin.eu).

Exploring Spoken Word Data in Oral History Archives

Forced alignment using FAVE and DARLA

Interest has grown in recent years in in oral history along with the increased popularity of the personal narrative. Oral history can be defined as the practice of eliciting people’s personal memory of lived experiences that are absent in written archives, and documenting them with a recording device with the purpose of turning the interviews into historical sources. The ‘digital turn’ has had an enormous impact on this archival practice. Currently much unique and valuable spoken language data reside in oral history archives, in the form of digital audio and video, written transcripts and non-digitized recordings. Speech and language technologists have developed various software tools and platforms for the analysis and exploration of the various layers of meaning in spoken data. But despite the large amount of research carried out in numerous disciplines to create, explore and analyse oral history data, the state of the art software is often not exploited by researchers in the humanities and the social sciences. At the same time oral history data is rather underused by linguists. CLARIN organized a workshop to bring together those doing research on oral history archive data, including archivists, language technologists, social scientists, along with linguists and speech technologists to investigate how these various communities might start to learn from each other and collaborate more effectively.

About

Exploring Spoken Word Data in Oral History Archives