CLARIN-PLUS workshop on Oral History

From 10-12 May 2017, CLARIAH WP5 attended a two-day CLARIN-PLUS workshop in Arezzo to discuss the development of an automatic transcription chain for Oral History that eventually could be integrated into the CLARIN infrastructure. The automatic transcription chain consists of a cascade of components, including automatic speech recognition, that help scholars to generate speech transcripts for interviews. CLARIAH WP5 was invited to the workshop to share technical and infrastructural experience on the development of such a transcription chain in the CLARIAH Media Suite, that currently is in progress. Also, CLARIAH took part in the discussion on scholarly requirements of transcription, given available techniques that were presented at the workshop by invited experts in the field.

In CLARIAH the approach is to embed transcription technology in the Media Suite and develop advanced features bottom-up gradually with a strong focus on generic workflows and sustainability. In CLARIN, the focus is on a stand-alone transcription service containing various advanced features such as alignment, manual transcription and correction tools, and transcription viewers. Moreover, in CLARIAH the assumption is that collections are already available within the infrastructure. In the CLARIN approach, collections can also exist locally with individual scholars that want to use transcription tools. It is useful to have these different approaches, as each one will provide complementary insights towards the development of transcription tools that fit the both practice and infrastructure context of scholars.

The envisaged CLARIN transcription service is a central ‘portal’ for scholars all over Europe that should be able to connect scholars to different transcription technologies ranging from speech recognition for different languages to manual correction tools. The speech recognition engine used in CLARIAH (operated by Beeld en Geluid and University of Twente) will also be used in the CLARIN service (operated by Radboud University).