Finding the Right DAM AI Tools: AVP’s Human-Centered Evaluation Framework

Henry Stewart DAM Webinars 2022

Watch the webinar with a searchable transcript and embedded closed captions here.

Audiovisual Metadata Platform Pilot Development (AMPPD) Final Project Report

This report documents the experience and findings of the Audiovisual Metadata Platform Pilot Development (AMPPD) project, which has worked to enable more efficient generation of metadata to support discovery and use of digitized and born-digital audio and moving image collections. The AMPPD project was carried out by partners Indiana University Libraries, AVP, University of Texas at Austin, and New York Public Library between 2018-2021.

Report Authors : Jon W. Dunn, Ying Feng, Juliet L. Hardesty, Brian Wheeler, Maria Whitaker, and Thomas Whittaker, Indiana University Libraries; Shawn Averkamp, Bertram Lyons, and Amy Rudersdorf, AVP; Tanya Clement and Liz Fischer, University of Texas at Austin Department of English. The authors wish to thank Rachael Kosinski and Patrick Sovereign for formatting and editing assistance.

Funding Acknowledgement: The work described in this report was made possible by a grant from the Andrew W. Mellon Foundation.

Read the entire report here.

PROBLEM STATEMENT

Libraries and archives hold massive collections of audiovisual recordings from a diverse range of timeframes, cultures, and contexts that are of great interest across many disciplines and communities.

In recent years, increased concern over the longevity of physical audiovisual formats due to issues of

media degradation and obsolescence, 2 combined with the decreasing cost of digital storage, have led institutions to embark on projects to digitize recordings for purposes of long-term preservation and improved access. Simultaneously, the growth of born-digital audiovisual content, which struggles with its own issues of stability and imminent obsolescence, has skyrocketed and continues to grow exponentially.

In 2010, the Council on Libraries and Information Resources (CLIR) and the Library of Congress reported in “The State of Recorded Sound Preservation in the United States: A National Legacy at Risk in the Digital Age” that the complexity of preserving and accessing physical audiovisual collections goes far beyond digital reformatting. This complexity, which includes factors such as the cost to digitize the originals and manage the digital surrogates, is evidenced by the fact that large audiovisual collections are not well represented in our national and international digital platforms. The relative paucity of audiovisual content in Europeana and the Digital Public Library of America is a testament to the difficulties that the GLAM (Galleries, Libraries, Archives, and Museums) community faces in creating access to their audiovisual collections. There has always been a desire for more audiovisual content in DPLA, even as staff members recognize the challenges and complexities this kind of content poses (massive storage requirements, lack of description, etc.). And, even though Europeana has made the collection of audiovisual content a focus of their work in recent years, as of February 2021, Europeana comprises 59% images and 38% text objects, but only 1% sound objects and 2% video objects. DPLA is composed of 25% images and 54% text, with only 0.3% sound objects, and 0.6% video objects.

Another reason, beyond cost, that audiovisual recordings are not widely accessible is the lack of sufficiently granular metadata to support identification, discovery, and use, or to support informed rights determination and access control and permissions decisions on the part of collections staff and users. Unlike textual materials—for which some degree of discovery may be provided through full-text indexing—without metadata detailing the content of the dynamic files, audiovisual materials cannot be located, used, and ultimately, understood.

Traditional approaches to metadata generation for audiovisual recordings rely almost entirely on manual description performed by experts—either by writing identifying information on a piece of physical media such as a tape cassette, typing bibliographic information into a database or spreadsheet, or creating collection- or series-level finding aids. The resource requirements and the lack of scalability to transfer even this limited information to a useful digital format that supports discovery presents an intractable problem. Lack of robust description stands in the way of access, ultimately resulting in the inability to derive full value from digitized and born-digital collections of audiovisual content, which in turn can lead to lack of interest, use, and potential loss of a collection entirely to obsolescence and media degradation.

Read the entire report here.