Towards Processing of the Oral History Interviews and Related Printed Documents

Towards Processing of the Oral History Interviews and Related Printed Documents Zbynˇek Zaj´ıc, Lucie Skorkovsk´a, Petr Neduchal, Pavel Ircing, Josef V. Psutka, Marek Hr´uz, Aleˇs Praˇz´ak, Daniel Soutner, Jan ˇSvec, Luk´aˇs Bureˇs and Ludˇek M¨uller University of West Bohemia, Faculty of Applied Sciences, NTIS - New Technologies for the Information Society and Department of Cybernetics Univerzitn´ı 8, 306 14 Plzeˇn, Czech Republic {zzajic, lskorkov, neduchal, ircing, psutka j, mhruz, aprazak, dsoutner, honzas, lbures, muller}@ntis.zcu.cz Abstract In this paper, we describe the initial stages of our project, the goal of which is to create an integrated archive of the recordings, scanned documents, and photographs that would be accessible online and would provide multifaceted search capabilities (spoken content, biographical information, relevant time period, etc.). The recordings contain retrospective interviews with the witnesses of the totalitarian regimes in Czechoslovakia, where the vocabulary used in such interviews consists of many archaic words and named entities that are now quite rare in everyday speech. The scanned documents consist of text materials and photographs mainly from the home archives of the interviewees or the archive of the State Security. These documents are usually typewritten or even handwritten and have really bad optical quality. In order to build an integrated archive, we will employ mainly methods of automatic speech recognition (ASR), automatic indexing and search in recognized recordings and, to a certain extent, also the optical character recognition (OCR). Other natural language processing techniques like topic detection are also planned to be used in the later stages of the project. This paper focuses on the processing of the speech data using ASR and the scanned typewritten documents with OCR and describes the initial experiments. Keywords: historical sources processing, automatic speech recognition, optical character recognition, document processing 1. Introduction The main objective of the project “System for permanent preservation of documentation and presentation of histori- cal sources from the period of totalitarian regimes” is the re- search and development of software tools for archiving and providing access to the historical resources gathered within the documentary mission of the Institute for the Study of Totalitarian Regimes (USTR) 1. This institute studies and impartially evaluates the two totalitarian periods of the his- tory of the Czech Republic: the time of the Nazi occu- pation (1939-1945) and the time of Communist totalitar- ian power (1948-1989), examines the anti-democratic and criminal activity of state bodies, especially its security ser- vices, as well as other organizations based on its ideology. For that purpose, USTR secures and makes accessible to the public the documents related to those periods of sup- pressed freedom and converts acquired documents into the electronic form. Within the documentation activities of the USTR, many documents and recordings are stored on the internal storage of the USTR and are made accessible for the researchers on DVDs or through a rudimentary digital storage services. Only a small fraction of the interviews contains the verba- tim text transcription – in most of the cases, the interested scholars must manually sift through the whole …

Content truncated to 500 words