An Automated Tagging Approach to Improve Search and Retrieval in a Radio Archive

Metadata

Publisher: SMPTE — White Plains, NY, USA
Doc Type: Journal Article
Content Type: Original Research
Abbreviated Title: SMPTE Mot. Imag J.
Volume: 124, No. 8, pp. 25–32
Abstract: Although a manual process guarantees accurate tagging of archive material, it is very time-consuming. Hence, not all media content in a big broadcast archive can be annotated sufficiently. A more automated tagging process could reduce the amount of unannotated content. This paper describes how speech technology is applied to archived content of one year of the Flemish Radio and Television Network's Radio 1 Dutch news to address the issue described. Different options are discussed and an automated approach is suggested. Techniques such as speech recognition, keyword spotting, and keyword extraction are combined to generate automatic annotations. A search engine prototype was implemented to assess the findability of the radio content. Results from the prototype show that the proposed automated approach can improve annotation and search efficiency significantly while still maintaining high precision. The results and lessons learned and presented are not only valuable to archivists, but to other professional users such as journalists and even end users.
Publication Date: 2015-11-01
DOI: 10.5594/j18635
ISSN: Print: 1545-0279 | Electronic: 2160-2492
Link: https://doi.org/10.5594/j18635
Author(s): M. Lycke
bio
Marieke Lycke studied electrical engineering (multimedia & signal processing) at the Katholieke Universiteit (KU) Leuven, Belgium. In 2012 she started as a researcher in VRTs Research & Innovation department where she specializes in media, mostly audio, analysis tools. She was involved in projects about employing speech and language technology in workflows for different kinds of media users: from journalist, archivist to end user. She is also a member of the EBU SCAIE group.
M. Matton
bio
Mike Matton is a senior researcher at VRT. He joined the research labs of the VRT broadcasting organization in October 2009, working on a research team on information management. His main research focuses on applying artificial intelligence techniques in the media domain, as well as methods for managing metadata, including metadata models. He has been involved in several European and national projects. Matton is chair of the expert group on automated information extraction within the EBU. He holds master's degrees in informatics and artificial intelligence and a Ph.D. in computer science from the KU Leuven. His Ph.D. research involved example-based methods for speech and pattern recognition.
L. Overmeire
bio
Luk Overmeire obtained a M.Sc. in electronics engineering at the University of Ghent, Belgium. Before joining VRT, he was a research engineer in Alcatel Bell working on software-based services and ADSL digital filter design, respectively. In 2002, he joined VRT's R&D department where he did research on metadata-based video encoding and rate control. Since 2004, he has led the competence group focusing on audiovisual content processing and file-based media production, respectively. Overmeire currently leads the research activities on enhanced end user experiences, multiplatform production workflows, and automated metadata applications. Recent research activities include innovative story creation tools based on speech technology. Overmeire is an active member of several EBU working groups. Since 1996, he was involved in patent applications and authored several papers in international conferences.
Keyword(s): Information Retrieval, Automatic Speech Recognition, Content Retrieval, Search Engines
Copyright: © 2015 Society of Motion Picture and Television Engineers, Inc.

Bibliographic Reference(s)

K. Demuynck, J. Roelens, D. Van Compernolle, and P. Wambacq, “SPRAAK: An Open Source Speech Recognition and Automatic Annotation Kit,” Proc. International Conference on Spoken Language Processing, pp. 495-498, Brisbane, Australia, Sept. 2008. EXTERNAL
P. Debevere, D. Van Deursen, D. Van Rijsselbergen, E. Mannens, M. Matton, R. De Sutter, and R. Van de Walle, “Enabling Semantic Search in a News Production Environment,” Proc. 5th International Conference on Semantic and Digital Media Technologies, Saarbrucken, Germany, Dec. 2010. EXTERNAL
N. Oostdijk and D. Broeder, “Een Databank van het Gesproken Nederlands,” Philologia Frisica, pp. 37-54, 2002. EXTERNAL
J. Odijk, STEVIN Programme, Project Results, NTU, 2011. EXTERNAL
P. Debevere, D. Van Deursen, E. Mannens, R. Van de Walle, K. Braeckman, and R. De Sutter, “Linking Thesauri to the Linked Open Data Cloud for Improved Media Retrieval,” Proc. 12th International Workshop on Image Analysis for Multimedia Interactive Services, Delft, The Netherlands, Apr. 2011. EXTERNAL
Y. Raimond, C. Lowis, R. Hodgson, and J. Tweed, “Automated Semantic Tagging of Speech Audio,” International World Wide Web Conference, pp. 405-408, France, Apr. 2012. EXTERNAL
P. Debevere, D. Van Deursen, E. Mannens, R. Van de Walle, K. Braeckman, and R. De Sutter, “Medialoep: Optimizing Search in a Broadcaster Archive,” Proc. 12th International Workshop on Image Analysis for Multimedia Interactive Services, Delft, The Netherlands, Apr. 2011. First presented at IBC 2014, Amsterdam, The Netherlands, 11-15 September 2014. This paper is published here by kind permission of the IBC. Copyright © IBC. THE AUTHORS Marieke Lycke studied electrical engineering (multimedia & signal processing) at the Katholieke Universiteit (KU) Leuven, Belgium. In 2012 she started as a researcher in VRTs Research & Innovation department where she specializes in media, mostly audio, analysis tools. She was involved in projects about employing speech and language technology in workflows for different kinds of media users: from journalist, archivist to end user. She is also a member of the EBU SCAIE group. EXTERNAL
EBU SCAIE group, https://tech.ebu.ch/groups/pscaie. EXTERNAL
A. Van den Bosch, G.J. Busser, W. Daelemans, and S. Canisius,, “An Efficient Memory-Based Morphosyntactic Tagger and Parser for Dutch,” Selected Papers of the 17th Computational Linguistics in the Netherlands Meeting, pp. 99-114, Leuven, Belgium, 2007. EXTERNAL
M. Matton and K. Braeckman, “Speech Recognition Tools in a Media Retrieval System,” Proc. 2011 ACM International Workshop on Automated Media Analysis and Production for Novel TV Services, pp. 19-24, New York, 2011. EXTERNAL
S.-H. Aziz, L. Vassallo, and F. Veri, “Speech to Text and Semantic Analysis, Our Working Experience. Automatically Generated Metadata,” Changing Sceneries Changing Roles Part VI: Metadata as the Cornerstone of Digital Archiving, selected paper from the FIAT/IFTA Media Management Seminar, Hilversum, Netherlands, pp. 125-133, 2013. EXTERNAL
K. Demuynck, T. Laureys, P. Wambacq, and D. Van Compernolle, “The ESAT 2008 System for N-Best Dutch Speech Recognition Benchmark,” Proc. IEEE ASRU Workshop, pp. 339-343, Merano, Italy, Dec. 2009. EXTERNAL
A.J.K. Thambirathnam, “Acoustic Keyword Spotting in Speech with Applications to Data Mining,” Ph.D. dissertation, pp. 9-84, Queensland University of Technology, Mar. 2005. EXTERNAL
A. Messina, L. Boch, G. Dimino, W. Bailer, P. Schallauer, W. Allasia, M. Groppo, M. Vigilante, R. Basili, “Creating Rich Metadata in the TV Broadcast Archives Environment: The PrestoSpace Project,” Second International Conference on Automated Production of Cross Media Content for Multi-Channel Distribution, pp. 193-200, Leeds, England, Dec. 2006. EXTERNAL
BBC Research and Development, World Service Radio Archive Prototype, http://worldservice.prototyping.bbc.co.uk/, 2013. EXTERNAL
BBC Research and Development, “The World Service Radio archive, Unlocking the BBC World Service archive,” http://www.bbc.co.uk/rd/projects/worldservice-archive-proto, 2011-2014. EXTERNAL

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-j18635.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree

Reference this Doc

Plain text (ISO 690 compliant)

Preview:

M. Lycke, M. Matton, and L. Overmeire; An Automated Tagging Approach to Improve Search and Retrieval in a Radio Archive, SMPTE Motion Imaging Journal ( Volume: 124, Issue: 8, November 2015); SMPTE, 2015. Available at https://doi.org/10.5594/j18635

Snippet:

M. Lycke, M. Matton, and L. Overmeire; An Automated Tagging Approach to Improve Search and Retrieval in a Radio Archive, SMPTE Motion Imaging Journal ( Volume: 124, Issue: 8, November 2015); SMPTE, 2015. Available at https://doi.org/10.5594/j18635

HTML (ISO 690 compliant)

Preview:

Snippet:

<span class="citation">M. Lycke, M. Matton, and L. Overmeire; <cite>An Automated Tagging Approach to Improve Search and Retrieval in a Radio Archive</cite>, SMPTE Motion Imaging Journal ( Volume: 124, Issue: 8, November 2015); SMPTE, 2015. Available at <a href="https://doi.org/10.5594/j18635" target="_blank" rel="noopener">https://doi.org/10.5594/j18635</a></span>

SMPTE's HTML Pub

Preview:

Snippet:

<li>
M. Lycke, M. Matton, and L. Overmeire; <cite id="bib-10-5594-j18635">An Automated Tagging Approach to Improve Search and Retrieval in a Radio Archive</cite>, SMPTE Motion Imaging Journal ( Volume: 124, Issue: 8, November 2015); SMPTE, 2015
<span class="doi">10.5594/j18635</span>
</li>