Automated Metadata Enrichment of Large Speech Radio Archives

Raimond, Yves; Lowis, Christopher; Hodgson, R.; Tinley, D.

doi:10.5594/j18370xy

Cited by 12 publications

(30 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The full description of this algorithm to extract topics from audio as well as its evaluation is available in [12]. The core algorithm and our evaluation dataset are available on our Github account 2 .…”

Section: From Audiomentioning

confidence: 99%

“…Ian Messiter) and to radio drama (e.g. "Play of the Week" and "African Theatre") -both 13 We think this is people tagging programmes with their duration, though the Wikipedia article for "30 minutes" http://en. wikipedia.org/wiki/30_Minutes_(disambiguation) is for various cultural works.…”

Section: Most Frequent Tags With Interactionsmentioning

confidence: 99%

“…For example if 'london' was found in the transcripts it could correspond to at least two possible DBpedia IRIs: d:London and d:London, Ontario. Our algorithm uses the structure of DBpedia itself to disambiguate and rank these candidate terms, and in particular a similarity measure capturing how close two IRIs are from each other in the DBpedia graph [12]. For example if the automated transcripts mention 'london', and 'england' a lot, our algorithm will pick d:London as the correct disambiguation for the former, as it is very close to one possible disambiguation of the latter, i.e.…”

Section: From Audiomentioning

confidence: 99%

“…We therefore developed a cloudbased infrastructure to process entire radio archives in a reasonable time [13]. With this infrastructure in place, we processed the 3 years of continuous audio in the archive within two weeks for a pre-determined cost and generated a collection of ranked Linked Data tags for each programme.…”

Section: From Audiomentioning

confidence: 99%

“…As mentioned above, 18% of the prototype's users have done at least one tagging action but that isn't a particularly good measure of current activity. Instead we use something Wikipedia defines as "Active users" -"registered users who have performed an action in the last 30 days" 12 . Using this metric at the time of writing there are 44 active users (1.2%).…”

Section: Editing Activitymentioning

confidence: 99%

See 4 more Smart Citations

The BBC World Service Archive prototype

Raimond¹,

Ferne²,

Smethurst³

et al. 2014

Journal of Web Semantics

View full text Add to dashboard Cite

Section: From Audiomentioning

confidence: 99%

Section: Most Frequent Tags With Interactionsmentioning

confidence: 99%

Section: From Audiomentioning

confidence: 99%

Section: From Audiomentioning

confidence: 99%

Section: Editing Activitymentioning

confidence: 99%

See 3 more Smart Citations

The BBC World Service Archive prototype

Raimond¹,

Ferne²,

Smethurst³

et al. 2014

Journal of Web Semantics

View full text Add to dashboard Cite

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

Raimond¹,

Smethurst²,

McParland³

et al. 2013

Advanced Information Systems Engineering

View full text Add to dashboard Cite

The BBC has a very large archive of programmes, covering a wide range of topics. This archive holds a significant part of the BBC's 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 BBC's 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 BBC's 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 BBC's 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.

show abstract

The impact of semantic annotation techniques on content-based video lecture recommendation

Dias

Barrére

Souza

2020

Journal of Information Science

View full text Add to dashboard Cite

Increasing videos available in educational content repositories makes searching difficult, and recommendation systems have been used to help students and teachers receive a content of interest. Speech is an important carrier of information in video lectures and is used by content-based video recommendation systems. Although automatic speech recognition (ASR) transcripts have been used in modern video recommendation systems, it is not clear how annotation techniques work with noisy text. This article presents an analysis on a set of semantic annotation techniques when applied to text extracted from video lecture speech and their impact on two tasks: annotation and similarity analysis. Experiments show that topic models have good results in this scenario. Besides, a new benchmark for this task has been created and researchers can use it to evaluate new techniques.

show abstract

Automated Metadata Enrichment of Large Speech Radio Archives

Cited by 12 publications

References 6 publications

The BBC World Service Archive prototype

The BBC World Service Archive prototype

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

The impact of semantic annotation techniques on content-based video lecture recommendation

Contact Info

Product

Resources

About