Yves Raimond

An Overview of Semantic Web Activities in the OMRAS2 Project

Abstract The use of cultural information is becoming increasingly important in music information research, especially in music retrieval and recommendation. While this information is widely available on the Web, it is most commonly published using proprietary Web Application Programming Interfaces (APIs). The Linked Data community is aiming at resolving the incompatibilities between these diverse data sources by building a Web of data using Semantic Web technologies. The OMRAS2 project has made several important contributions to this by developing an ontological framework and numerous software tools, as well as publishing music related data on the Semantic Web. These data and tools have found their use even beyond their originally intended scope. In this paper, we first provide a broad overview of the Semantic Web technologies underlying this work. We describe the Music Ontology, an open-ended framework for communicating musical information on the Web, and show how this framework can be extended to describe specific sub-domains such as music similarity, content-based audio features, musicological data and studio production. We describe several data-sets that have been published and data sources that have been adapted using this framework. Finally, we provide application examples ranging from software libraries to end user Web applications.

Interlinking Music-Related Data on the Web

This article describes how semantic Web technologies can be used to interlink musical data sources that have traditionally been isolated and difficult to integrate.

The BBC World Service Archive prototype

Most broadcasters have accumulated large audio and video archives stretching back over many decades. For example the BBC World Service radio archive includes around 70,000 English-language programmes from over 45źyears. This amounts to about three years of continuous audio and around 15źTB of data. The metadata around this archive is sparse and sometimes wrong, but the full audio content is available in digital form. We have built a system to process the existing audio and text and automatically annotate programmes within the archive with Linked Data web identifiers. The resulting interlinks are used to bootstrap search and navigation within this archive and expose it to users. Automated data will never be entirely accurate so we built crowdsourcing mechanisms for users to correct and add data. The resulting crowdsourced data is then used to improve search and navigation within the archive, as well as evaluate and improve our algorithms. As a result of this feedback cycle, the interlinks between our archive and the Semantic Web are continuously improving. This unique combination of Semantic Web technologies, automation and crowdsourcing has dramatically reduced the amount of time and effort required to publish this rich archive online. The BBC World Service archive prototype is available online at http://worldservice.prototyping.bbc.co.uk, last accessed March 2014.

ZemPod: A semantic web approach to podcasting

In this paper we present a semantic web approach to solve some current limitations of podcasting. The main shortcomings of podcasts are two. The first one is that there is no formal description of the contents of a podcast session, apart from a textual description only available in HTML. The second problem is that a podcast session consists of a single audio file. Thus, it is very difficult to seek into one of the music tracks that compose a podcast. Our proposal to cope with these problems uses traditional audio signal processing - such as speech versus music segmentation, and audio identification -, and semantic web techniques to automatically describe and decompose the audio content of a podcast session. Yet, we believe that adding semantics to the podcast to explain its content, and decomposing it into smaller and meaningful chunks (that permits seeking into the inner parts of the file) will ease important music information retrieval tasks, such as recommendation, filtering and discovery.

Automated semantic tagging of speech audio

The BBC is currently tagging programmes manually, using DBpedia as a source of tag identifiers, and a list of suggested tags extracted from the programme synopsis. These tags are then used to help navigation and topic-based search of programmes on the BBC website. However, given the very large number of programmes available in the archive, most of them having very little metadata attached to them, we need a way to automatically assign tags to programmes. We describe a framework to do so, using speech recognition, text processing and concept tagging techniques. We describe how this framework was successfully applied to a very large BBC radio archive. We demonstrate an application using automatically extracted tags to aid discovery of archive content.

Using the Past to Explain the Present: Interlinking Current Affairs with Archives via the Semantic Web

The BBC has a very large archive of programmes, covering a wide range of topics. This archive holds a significant part of the BBCs institutional memory and is an important part of the cultural history of the United Kingdom and the rest of the world. These programmes, or parts of them, can help provide valuable context and background for current news events. However the BBCs archive catalogue is not a complete record of everything that was ever broadcast. For example, it excludes the BBC World Service, which has been broadcasting since 1932. This makes the discovery of content within these parts of the archive very difficult. In this paper we describe a system based on Semantic Web technologies which helps us to quickly locate content related to current news events within those parts of the BBCs archive with little or no pre-existing metadata. This system is driven by automated interlinking of archive content with the Semantic Web, user validations of the resulting data and topic extraction from live BBC News subtitles. The resulting interlinks between live news subtitles and the BBCs archive are used in a dynamic visualisation enabling users to quickly locate relevant content. This content can then be used by journalists and editors to provide historical context, background information and supporting content around current affairs.

A distributed data space for music-related information

In this paper, we describe how some key Semantic Web technologies can be used to gather in a single distributed knowledge environment several music-related sources of information, from digital archives to feature extractors or personal music collections. Such knowledge can then be used for a wide range of purposes, such as aggregation and information retrieval, visualisation and enriched access, or cross-repository interlinking. We also describe on-going efforts aiming at bootstrapping such a data-space, as well as preliminary results.

A scalable framework for multimedia knowledge management

In this paper, we describe a knowledge management framework that addresses the needs of multimedia analysis projects and provides a basis for information retrieval systems. The framework uses Semantic Web technologies to provide a shared knowledge environment, and active Knowledge Machines, wrapping multimedia processing tools, to exploit and/or export knowledge to this environment. This framework is able to handle a wide range of use cases, from an enhanced workspace for researchers to end-user information access. As an illustration of how the proposed framework can be used, we present a case study of music analysis.