Modular System Design for Multimedial Information Handling

Botond Pakucs 1 Bj#rn Gamb#ck 1;2 Preben Hansen 1
botte@sics.se gamback@sics.se preben@sics.se
1 Information and Language Engineering 2 Computational Linguistics
Swedish Institute of Computer Science University of Helsinki
Box 1263, S164 29 Kista, Sweden P.O. Box 4, SF00014 Helsinki, Finland

Abstract
Often, information retrieval from various other
media is analogous to textbased retrieval; how
ever, accessing documents in e.g. audio or video
formats causes some extra problems, in particular
with respect to document segmentation, choice
of indexing features, and robustness. We review
these diOEculties, together with some previous at
tempts to overcome them, and then describe a
very AEexible, modular IR system which has been
designed with a specic eye towards these issues.


References
Abberley, D., Renals, S., and Cook, G. 1998.
Retrieval of Broadcast News Documents
with the THISL System. Proc. Int.
Conf. on Acoustics, Speech and Signal
Processing, Seattle, Washington. IEEE.
Bretan, I., Dewe, J., Hallberg, A., Karlgren, J.,
and Wolkert, N. 1998. WebSpecic
Genre Visualization. Proc. 3rd World
Conf. on the WWW and Internet, Orlando, FL. AACE.
Bub, T., Wahlster, W., and Waibel, A. 1997.
Verbmobil: The Combination of Deep
and Shallow Processing for Spontaneous
Speech Translation. Proc. Int. Conf. on
Acoustics, Speech and Signal Processing,
pp. 7174, M#nchen, Germany. IEEE.
Crestani, F. and Sanderson, M. 1997. Retrieval
of Spoken Documents: First Experiences. 
Technical report, Dept. of Com
puting Science, University of Glasgow,
Scotland.
Falk, J. 1997. Pauses in Synthesized Speech: 
Automatic Prediction of Silent Intervals in
Swedish. MA Thesis, Dept. of Linguistics, 
G#teborg University, Sweden.
Garofolo, J. S., Voorhees, E. M., Stanford, V.,
and Jones, K. S. 1997. TREC6
1997 Spoken Document Retrieval Track
Overview and Results. Proc. 6th Text
Retrieval Conf., pp. 8391, Gaithersburg, MD. NIST.
Glavitsch, U. and Sch#uble, P. 1992. A System
for Retrieving Speech Documents. Proc.
15th Int. Conf. on Research and Development in Information Retrieval, pp.
168176, K#benhavn, Denmark. ACM
SIGIR.
Glavitsch, U., Sch#uble, P., and Wechsler, M.
1994. Metadata for Integrating Speech
Documents in a Text Retrieval System.
SIGMOD Record, 23(4):5763.
Hauptmann, A. G. 1995. Speech Recognition in
the Informedia TM Digital Library: Uses
and Limitations. Proc. 7th Int. Conf. on
Tools with AI, Washington, DC. IEEE.
James, D. A. 1995. The Application of Classical Information Retrieval Techniques to
Spoken Documents. PhD Thesis, Engineering Dept., University of Cambridge,
England.
Jones, G. J. F., Foote, J. T., Sparck Jones, K.,
and Young, S. J. 1996. Retrieving Spoken Documents by Combining Multiple
Index Sources. Proc. 19th Int. Conf.
on Research and Development in In
formation Retrieval, pp. 3038, Z#rich,
Switzerland. ACM SIGIR.
Marchionini, G. 1995. Information Seeking in
Electronic Environments. Cambridge
University Press, Cambridge, England.
Ng, K. 1998. Towards Robust Methods for Spoken Document Retrieval. Proc. 5th Int.
Conf. on Spoken Language Processing,
Sydney, Australia.
Ng, K. and Zue, V. 1997. Subword Unit Representations for Spoken Document 
Retrieval. Proc. 5th European Conf. on
Speech Communication and Technology,
pp. 16071610, Rhodes, Greece.
Robinson, T., Hochberg, M., and Renals, S. 1996.
The Use of Recurrent Networks in Continuous Speech Recognition. In Lee, C.
H. and Soong, F. K., editors, Advanced
Topics in Automatic Speech and Speaker
Recognition, Ch. 7. Kluwer, Dordrecht,
Holland.
Sanderson, M. and Crestani, F. 1998. Mixing
and Merging for Spoken Document Retrieval. Proc. 2nd European Conf. on
Research and Advanced Technology for
Digital Libraries, pp. 397407, Heraklion, Greece.
Slaughter, L., Oard, D., Warnick, V., Harding, J., and Wilkerson, G. 1998. A
Graphical Interface for SpeechBased
Retrieval. Proc. 3rd Digital Library
Conf., Philadelphia, PA. ACM.
Smeaton, A., Morony, M., Quinn, G., and Scaife,
R. 1998. Taisc#ala#: Information Retrieval from an Archive of Spoken 
Radio News. Proc. 2nd European Conf. on
Research and Advanced Technology for
Digital Libraries, pp. 397407, Heraklion, Greece.
Wechsler, M. 1995. Eine neue Indexierungsmeth
ode f#r Information Retrieval auf
Audiodokumente. HIM95 Konferenz:
HypertextInformation RetrievalMultimedia, pp. 117128. (in German).
