Publication Details

Information Retrieval from Spoken Documents

FAPŠO, M.; SMRŽ, P.; SCHWARZ, P.; SZŐKE, I.; SCHWARZ, M.; ČERNOCKÝ, J.; KARAFIÁT, M.; BURGET, L. 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. p. 410-416. ISBN: 3-540-32205-1.
Czech title
Information Retrieval from Spoken Documents
Type
conference paper
Language
English
Authors
Fapšo Michal, Ing., Ph.D.
Smrž Pavel, doc. RNDr., Ph.D. (DCGM)
Schwarz Petr, Ing., Ph.D. (DCGM)
Szőke Igor, Ing., Ph.D. (DCGM)
Schwarz Milan
Černocký Jan, prof. Dr. Ing. (DCGM)
Karafiát Martin, Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
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)
ISBN
3-540-32205-1
Publisher
Springer Verlag
Place
Mexico City
BibTeX 
@inproceedings{BUT22168,
  author="Michal {Fapšo} and Pavel {Smrž} and Petr {Schwarz} and Igor {Szőke} and Milan {Schwarz} and Jan {Černocký} and Martin {Karafiát} and Lukáš {Burget}",
  title="Information Retrieval from Spoken Documents",
  booktitle="Proceedings of the Seventh International Conference on Intelligent Text Processing and Computational Linguistics (CICLING 2006)",
  year="2006",
  pages="410--416",
  publisher="Springer Verlag",
  address="Mexico City",
  isbn="3-540-32205-1"
}
Back to top