This paper discusses the application of speech alignment, image processing, and language understanding technologies to build efficient interfaces into large digital oral history archives, as exemplified by a thousand hour HistoryMakers corpus. Browsing, querying, and navigation features are discussed.
As the Kentucky representative in the National Digital Newspaper Program (NDNP), the University of Kentucky Libraries Preservation and Digital Programs (UKPDP) team has worked extensively with historic newspaper digitization from microfi lm over the last four years, using both an in-house production methodology and vendor resources. With more than 50 years experience with microfi lming newspapers added to that, UKPDP is well versed with issues related to historic newspapers on microfi lm. "Digitizing historic newspapers from microfi lm" may sound as if all the work lies in the mechanics of digitization. Our experience tells us otherwise. If the digital surrogates are to be an accurate representation of the newspaper, there are several points to consider beforehand that have little or nothing to do with the digitization itself but, rather, with the newspapers and how they were microfi lmed. This article identifi es the more pressing of these issues and offers some solutions for them. It does not address in detail the more complicated affair of hardware, software, interface access, or storage associated with the digitization.
A Brief History: Newspapers
A Brief History: Microfi lm at the University of KentuckyWithout the mass of historic newspapers on microfi lm that
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.