Publication Details

Information Retrieval from Spoken Documents

FAPŠO Michal, SMRŽ Pavel, SCHWARZ Petr, SZŐKE Igor, SCHWARZ Milan, ČERNOCKÝ Jan, KARAFIÁT Martin and BURGET Lukáš. Information Retrieval from Spoken Documents. In: Proceedings of the Seventh International Conference on Intelligent Text Processing and Computational Linguistics (CICLING 2006). Mexico City: Springer Verlag, 2006, pp. 410-416. ISBN 3-540-32205-1.
Czech title
Information Retrieval from Spoken Documents
Type
conference paper
Language
english
Authors
Fapšo Michal, Ing. (FIT BUT)
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT)
Schwarz Petr, Ing., Ph.D. (DCGM FIT BUT)
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT)
Schwarz Milan (Phonexia)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

multimedia information retrieval, speech databases

Abstract

This paper describes a designed and implemented system for efficient storage,
indexing and search in collections of spoken documents that takes advantage
of  automatic speech recognition. As the quality of current speech
recognizers is not sufficient for a great deal of applications, it is
necessary to index the ambiguous output of the recognition, i.\,e. the
acyclic graphs of word hypotheses --- recognition lattices. Then, it is not
possible to directly apply the standard methods known from text-based systems.
The paper discusses an optimized indexing system for efficient search in the
complex and large data structure that has been developed by our group. The
search engine works as a server. The meeting browser JFerret, developed withing
the European AMI project,  is used as a client to browse search results.

Published
2006
Pages
410-416
Proceedings
Proceedings of the Seventh International Conference on Intelligent Text Processing and Computational Linguistics (CICLING 2006)
Conference
Conference on Intelligent Text Processing and Computational Linguistics, Mexico City, Mexico, MX
ISBN
3-540-32205-1
Publisher
Springer Verlag
Place
Mexico City, MX
BibTeX 
@INPROCEEDINGS{FITPUB7922,
   author = "Michal Fap\v{s}o and Pavel Smr\v{z} and Petr Schwarz and Igor Sz\H{o}ke and Milan Schwarz and Jan \v{C}ernock\'{y} and Martin Karafi\'{a}t and Luk\'{a}\v{s} Burget",
   title = "Information Retrieval from Spoken Documents",
   pages = "410--416",
   booktitle = "Proceedings of the Seventh International Conference on Intelligent Text Processing and Computational Linguistics (CICLING 2006)",
   year = 2006,
   location = "Mexico City, MX",
   publisher = "Springer Verlag",
   ISBN = "3-540-32205-1",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/7922"
}
Back to top