Accessing the spoken word

Abstract

Spoken word audio collections cover many domains, including radio and television broadcasts, oral narratives, governmental proceedings, lectures, and telephone conversations. The collection, access and preservation of such data is stimulated by political, economic, cultural and educational needs. This paper outlines the major issues in the field, reviews the current state of technology, examines the rapidly changing policy issues relating to privacy and copyright, and presents issues relating to the collection and preservation of spoken audio content.

Access to recorded interviews

“…Moreover, standardization efforts typically focus more on what can be encoded than on what must be encoded so selective implementation can also lead so incompatibilities. Recent overviews of current practices in the cultural heritage domain can be generated in the context of IST-FP6 project MultiMatch (Multilingual/Multimedia Access To Cultural Heritage see Oomen and Smulders [2006] and Goldman et al [2003]) development and use of metadata models is also one of the focuses of the IST-FP6 Coordination Action CHORUS for multimedia content search engines.…”

“…As acquisition and storage costs have declined over the past several decades, it has become increasingly apparent that fully manual techniques for providing access to oral history collections can affordably meet just a small fraction of the potential need. In 2002, the DELOS/NSF working group in Spoken Word Audio Collections met to discuss an agenda in the area of spoken word archives and collaborative research projects [Goldman et al 2005]. A number of items from that agenda have since been taken up in research projects.…”

“…There is a considerable range of tools and technologies available that could be deployed to improve access to spoken word collections [Goldman et al 2005]. Besides the substantial effort that has been devoted to development of technology for content-based access to audiovisual archives in general, several initiatives have successfully been undertaken to apply some of this technology to cultural heritage collections.…”

Interactive visualisation techniques for dynamic speech transcription, correction and training

“…Transcription systems are wide and varied in their uses, which include dictation [23] as well as audio [8,7], multimedia [6,25,18] and meeting indexing applications [24,22]. However, since even the most sophisticated automatic speech recognition systems are far from perfect, transcriptions produced by their application often contain errors.…”

Tools for Searching, Annotation and Analysis of Speech, Music, Film and Video A Survey

“…As far as possible, we have avoided addressing technical problems specific to single disciplines. Other recent publications have examined related issues of resources, access, and preservation (BUFVC, 2004;British Academy, 2005), though publications which deal also with issues of technology have generally focused only on speech (SWAG, 2003;Goldman et al, 2005;Koumpis & Renals, 2005;Lee & Chen 2005;Ostendorf et al, 2005).…”