I was delighted and intrigued to read an article in the March 26, 2014 web edition of the Chronicle of Higher Education: Scholars Collaborate to Make Sound Recordings More Accessible. It described a project spearheaded by Tanya Clement, former University of Maryland employee, creator of In Transition: Selected Poems by the Baroness Elsa von Freytag-Loringhoven, and now assistant professor at the University of Texas at Austin.
I am always on the lookout for “cool tools” that we may consider using some day for our own work, and their are a lot out there. The HiPSTAS Research and Development with Repositories (HRDR) project is funded by an NEH Institute for Advanced Topics in the Digital Humanities grant to develop and evaluate a computational system for librarians and archivists for discovering and cataloging sound collections. From the HiPSTAS blog:
The HRDR project will include three primary products: (1) a release of ARLO (Automated Recognition with Layered Optimization) that leverages machine learning and visualizations to augment the creation of descriptive metadata for use with a variety of repositories (such as a MySQL database, Fedora, or CONTENTdm); (2) a Drupal ARLO module for Mukurtu, an open source content management system, specifically designed for use by indigenous communities worldwide; (3) a white paper that details best practices for automatically generating descriptive metadata for spoken word digital audio collections in the humanities.
I, for, one, am looking forward to the output of this project, and at the prospect of a faster way to increase access to our fragile sound recordings.