Workshops

WS01: Sound Safari

Date: Monday, September 23 

Time: 09:00am - 10:30am

Maximum number of participants: 40

The 'Sound Safari' workshop is designed to offer a hands-on exploration of multimodal models and their applications in cataloging, information retrieval, and Artificial Intelligence. It enables attendees to delve into avant-garde AI-based technologies that convert images into both sound and textual descriptions. Through physical exploration and practical engagement, our goal is to nurture a deep-seated analysis of the consequences of these technologies, the emerging narratives they weave, spotlighting biases and the hurdles posed by non-standard images, and their ramifications for the automated cataloging of archives.

Furthermore, this workshop is dedicated to uncovering the wealth of interdisciplinary collaboration. It invites participants from diverse fields to contribute with their distinct viewpoints, thereby enriching the discourse and widening our collective insight into AI's significance within the realm of archival science.

Structured to be highly interactive, the workshop is divided into three parts: an introductory overview of multimodal models and their practical uses; a fieldwork excursion, wherein participants will walk around the conference environment to capture images, which they will then convert into sound, text and images again via AI models; culminating in a time for sharing and discussing the insights and outcomes derived from these activities.

To ensure participants can fully engage in the workshop, they are kindly asked to bring their laptops.

WS02: Low-Cost Preservation: Audio Digitisation with Raspberry Pi

Date: Monday, September 23 

Time: 09:00am - 10:30am

Maximum number of participants: 40

In a time of budget constraints across heritage projects worldwide, the preservation of sound collections is becoming an increasing challenge, especially for archives without existing digitisation solutions. At the same time, advances in technology present opportunities to deviate from ‘traditional’ digitisation systems – the hardware and software commonly associated with audio production and preservation.In response to this changing economic and technological environment, we have been investigating the potential of a low-cost and versatile solution for audio digitisation using the Raspberry Pi single-board computer. We will share our findings about the viability, capability and utility of a low-cost, ARM Linux-based audio digitisation workstation to enable archives to achieve preservation-standard transfers without the overheads of a typical desktop computer system.
 

WS03: Using AI to make spoken-word content more accessible and discoverable 

Date: Monday, September 23 

Time: 09:00am - 10:30 am

Maximum number of participants: 40

Generative AI coupled with more traditional AI such as Automatic Speech Recognition (ASR) present unique opportunities for the categorization, discoverability, accessibility and dissemination of spoken word media. In this presentation Mark Boas, CTO of TheirStory and co-founder of the Hyperaudio Project will discuss methods of exposing media in a form that facilitates search, sharing and even remixing using the open-source tools he has been involved in developing for the last decade. The last 12 months has seen a sea change in the emergence of generative AI such as LLMs, at the same time we’ve seen speech-to-text algorithms improve in accuracy and speed, while costs continue to fall. His work at TheirStory, focussing on stories from underrepresented and marginalized communities, seeks to combine word-timed machine generated interactive transcripts with emerging generative AI to create metadata that facilitates the surfacing of content and its re-use in formats by students and other communities. Believing that these technologies should be able to be leveraged by the wider community, much of this work adheres to open standards and has been released under open-source licenses in forms that can be mixed, matched and integrated into other platforms. Mark will take us on a whistle-stop tour of these new innovative technologies, explaining the concepts behind them and the pros and cons of each. Touching on the ethics of AI he’ll talk about the wider aim of engaging the oral-history archival community and fostering collaboration around open technologies to help expose this important aspect of our history.
 

WS04: Managing Collections with Audiovisual Metadata Tools

Date: Monday, September 23 

Time: 11:00am - 12:30pm

Maximum number of participants: 40

As audiovisual content and formats become increasingly complex, the need to capture descriptive and technical metadata about audiovisual assets becomes ever-more pressing – and while asset management systems may come and go, the metadata contained in those systems shouldn’t disappear with them. This half-day workshop will focus on capturing accurate, standardized metadata that can be mapped and migrated between different systems using the PBCore schema. Beginning with an introduction to key concepts in audiovisual metadata and a walk-through of the structure of the PBCore schema, the workshop will provide hands-on exercises in audiovisual cataloging using the PBCore Cataloging Tool to create XML records and MediaInfo to capture technical metadata about digital files. Attendees will learn about best practices for controlled vocabularies and standardized data fields, be presented with real-world use cases for PBCore records, and practice conceptual metadata mapping into databases. Although the workshop will be presented in English, tools and resources will also be available in Spanish thanks to the NEH-funded PBCore Education and Training Project.

WS05: Building Digital Preservation Capabilities

Date: Monday, September 23 

Time: 09:00am - 12:30pm

Maximum number of participants: 40

The preservation of digital materials is not a static activity. To create an enduring archive of digital content requires constant advocacy effort and partnership to proactively manage the organizational and technological infrastructures we deploy - particularly in times of crisis, when resources are so stretched.  Applying a carefully considered approach to continuous improvement of digital preservation capabilities can greatly benefit practitioners when looking to set and achieve objectives, sharing and embedding this responsibility across whole organizations. This workshop aims to provide attendees with the skills and tools to develop and implement a methodology for continuous improvement at their organization. The Digital Preservation Coalition (DPC) has created resources to facilitate this process. The newest resource is the DPC Competency Framework with accompanying audit toolkit (DPC CAT) and example role descriptions. The workshop will begin by providing attendees with an understanding of the importance and benefits of a continuous improvement approach to benchmarking their digital preservation capabilities. Following this, attendees will be provided with an introduction to the Competency Framework, before being guided through a practical exercise allowing them to audit their own digital preservation skills using DPC CAT. The workshop will finish with an overview of other DPC resources that can help practitioners with planning and advocating for their digital preservation activities. This workshop will benefit individuals and organizations from across many sectors who wish to assess their current digital preservation capabilities and plan for future developments.