Related papers: Unsilencing Colonial Archives via Automated Entity…
After decades of massive digitisation, an unprecedented amount of historical documents is available in digital format, along with their machine-readable texts. While this represents a major step forward with respect to preservation and…
The digitisation campaigns carried out by libraries and archives in recent years have facilitated access to documents in their collections. However, exploring and exploiting these documents remain difficult tasks due to the sheer quantity…
Voice anonymisation is used to conceal voice identity while preserving linguistic content. Even if anonymisation seems strong, non-timbral cues such as accent that remain post-anonymisation can help re-identification and reveal sensitive…
Archives play a crucial role in the construction and advancement of society. Humans place a great deal of trust in archives and depend on them to craft public policies and to preserve languages, cultures, self-identity, views and values.…
Voice digital assistants must keep up with trending search queries. We rely on a speech recognition model using contextual biasing with a rapidly updated set of entities, instead of frequent model retraining, to keep up with trends. There…
In this study, we leverage a unique UNESCO collection of mid-20th century radio recordings to probe the robustness of modern off-the-shelf language identification (LID) and speaker recognition (SR) methods, especially with respect to the…
A growing body of work shows that many problems in fairness, accountability, transparency, and ethics in machine learning systems are rooted in decisions surrounding the data collection and annotation process. In spite of its fundamental…
Information integration applications, such as mediators or mashups, that require access to information resources currently rely on users manually discovering and integrating them in the application. Manual resource discovery is a slow…
Despite the plethora of born-digital content, vast troves of important content remain accessible only on physical media such as paper or microfilm. The traditional approach to indexing undigitized content is using manually created metadata…
Recent advances in artificial intelligence, including the development of highly sophisticated large language models (LLM), have proven beneficial in many real-world applications. However, evidence of inherent bias encoded in these LLMs has…
This paper presents a use case exploring the application of the Archival Resource Key (ARK) persistent identifier for promoting and maintaining ontologies. In particular, we look at improving computation with an in-house ontology server in…
While colonization has sociohistorically impacted people's identities across various dimensions, those colonial values and biases continue to be perpetuated by sociotechnical systems. One category of sociotechnical systems--sentiment…
This paper introduces annotative indexing, a novel framework that unifies and generalizes traditional inverted indexes, column stores, object stores, and graph databases. As a result, annotative indexing can provide the underlying indexing…
Data anonymization is often a task carried out by humans. Automating it would reduce the cost and time required to complete this task. This paper presents a pipeline to automate the anonymization of audio data in French. We propose a…
For many of the 700 million illiterate people around the world, speech recognition technology could provide a bridge to valuable information and services. Yet, those most in need of this technology are often the most underserved by it. In…
With the AI revolution in place, the trend for building automated systems to support professionals in different domains such as the open source software systems, healthcare systems, banking systems, transportation systems and many others…
Properly annotated multimedia content is crucial for supporting advances in many Information Retrieval applications. It enables, for instance, the development of automatic tools for the annotation of large and diverse multimedia…
Named entity recognition (NER) aims to identify mentions of named entities in an unstructured text and classify them into predefined named entity classes. While deep learning-based pre-trained language models help to achieve good predictive…
Many archival recordings of speech from endangered languages remain unannotated and inaccessible to community members and language learning programs. One bottleneck is the time-intensive nature of annotation. An even narrower bottleneck…
Author name disambiguation in bibliographic databases is the problem of grouping together scientific publications written by the same person, accounting for potential homonyms and/or synonyms. Among solutions to this problem, digital…