Taiscéalaí: Information Retrieval from an Archive of Spoken Radio News

  • Alan F. Smeaton
  • M. Morony
  • Gerard Quinn
  • Ronan Scaife
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1513)

Abstract

In this paper we describe Taiscéalaí, a web-based system which provides content-based retrieval on an up-to-date archive of RTé radio news bulletins. Taiscéalaí automatically records and indexes news bulletins twice daily using a stream of phones recognised from the raw audio data. A user’s typed query is matched against fixed length windows from the broadcasts. A user interface allows the news bulletins most likely to be relevant to be presented and the user to select sub-parts of the bulletins to be played. Many of the parameters we have chosen to use such as the size and amount of overlap of windows and the weighting of phones within those windows, have been determined within the framework of the TREC Spoken Document Retrieval track and are thus well-founded. We conclude the paper with a walkthrough of a worked example retrieval and an outline of our plans for extending Taiscéalaí into an integrated digital library for news.

Keywords

Information Retrieval Speech Recognition Digital Library European Monetary Union News Broadcast 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bakis, R., Chen, S., Gopalakrishnan, P., Gopinath, R., Maes, S. Polymenakos, L.: Transcription of Broadcast News-System Robustness Issues and Adaptation Techniques. In: Proceedings of the ICASSP 1 (1997) 711–714Google Scholar
  2. 2.
    Gauvain, J.L., Adda, G., Lamel, L., Adda-Decker, M.: Transcribing Broadcast News Shows. In: Proceedings of the ICASSP 1 (1997) 715–718Google Scholar
  3. 3.
    Harman, D.K., Voorhees, E.M.: Proceedings of the Sixth Text Retrieval Conference. (in press) (1998) Available at http://trec.nist.gov/
  4. 4.
    Kelledy, F., Smeaton, A.F.: TREC-5 Experiments at Dublin City University: Query Space Reduction, Spanish Stemming and Character Shape Coding. In: Proceedings of the Fifth Text Retrieval Conference (TREC-5), Voorhees, E.M. and Harman, D.K. (Eds.), NIST Special Publication 500-238 (1997) 57–64Google Scholar
  5. 5.
    Morony, M.: Description of the Speech Processing Used in the Taiscéalaí System. Available at http://lorca.compapp.dcu.ie/RTE/technical.html (1998)
  6. 6.
    Ng, K., Zue, V.W.: An Investigation of Subword Unit Representations for Spoken Document Retrieval. Poster presented at SIGIR97, available at http://www.sis.lcs.mit.edu/kng/papers/sigir97.ps (1997)
  7. 7.
    Quinn, G.: Experiments on the Performance of a Retrieval System for Radio News (in preparation), (1998)Google Scholar
  8. 8.
    Schäuble, P., Weschler, M.: First Experiences with a System for Content Based Retrieval of Information from Speech Recordings. In: Proceedings of the IJCAI Workshop on Intelligent Multimedia Information Retrieval. Available at http://www-ir.inf.ethz.ch/ISIR-Papers.html (1995)
  9. 9.
    Smeaton, A.F., Kelledy, F., Quinn, G.: Ad hoc Retrieval Using Thresholds, WSTs for French Mono-Lingual Retrieval, Document-at-a-Glance for High Precision and Triphone Windows for Spoken Documents. In: Proceedings of the Sixth Text Retrieval Conference. Voorhees, E.M. and Harman, D.K. (Eds.) (in press) (1998) Available http://trec.nist.gov/
  10. 10.
    Smeaton, A.F., Burnett, M., Crimmins, F., Quinn, G.: An Architecture for Efficient Document Clustering and Retrieval on a Dynamic Collection of Newspaper Texts. In: Proceedings of the BCS-IRSG Colloquium, Springer Workshops in Computing (in press) (1998)Google Scholar
  11. 11.
    Woodland, P.C., Gales, M.J.F., Pye, D., Young, S.J.: Broadcast News Transcription Using HTK. In: Proceedings of the ICASSP 1 (1997) 719–722Google Scholar
  12. 12.
    Young, S.J., Odell, J.J., Woodland, P.C.: Tree-Based State Tying for High Accuracy Acoustic Modelling. In: Proceedings of the ARPA Workshop on Human Language Technology (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Alan F. Smeaton
    • 1
  • M. Morony
    • 2
  • Gerard Quinn
    • 1
  • Ronan Scaife
    • 2
  1. 1.School of Computer ApplicationsDublin City UniversityGlasnevin, Dublin 9Ireland
  2. 2.School of Electronic EngineeringDublin City UniversityGlasnevin, Dublin 9Ireland

Personalised recommendations