Detail publikace

Information Retrieval from Spoken Documents

FAPŠO, M. SMRŽ, P. SCHWARZ, P. SZŐKE, I. SCHWARZ, M. ČERNOCKÝ, J. KARAFIÁT, M. BURGET, L.

Originální název

Information Retrieval from Spoken Documents

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

multimedia information retrieval, speech databases

Autoři

FAPŠO, M.; SMRŽ, P.; SCHWARZ, P.; SZŐKE, I.; SCHWARZ, M.; ČERNOCKÝ, J.; KARAFIÁT, M.; BURGET, L.

Rok RIV

2006

Vydáno

29. 9. 2006

Nakladatel

Springer Verlag

Místo

Mexico City

ISBN

3-540-32205-1

Kniha

Proceedings of the Seventh International Conference on Intelligent Text Processing and Computational Linguistics (CICLING 2006)

Strany od

410

Strany do

416

Strany počet

6

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"
}