Detail publikace

Comparison of methods for language-dependent and language-independent query-by-example spoken term detection

TEJEDOR, J. FAPŠO, M. SZŐKE, I. ČERNOCKÝ, J. GRÉZL, F.

Originální název

Comparison of methods for language-dependent and language-independent query-by-example spoken term detection

Typ

článek v časopise - ostatní, Jost

Jazyk

angličtina

Originální abstrakt

This article investigates query-by-example (QbE) spoken term detection (STD), in which the query is not entered as text, but selected in speech data or spoken. Two feature extractors based on neural networks (NN) are introduced: the first producing phone-state posteriors and the second making use of a compressive NN layer. They are combined with three different QbE detectors: while the Gaussian mixture model/hidden Markov model (GMM/HMM) and dynamic time warping (DTW) both work on continuous feature vectors, the third one, based on weighted finite-state transducers (WFST), processes phone lattices.

Klíčová slova

Experimentation, Query-by-example, DTW-based query-by-example, GMM/HMM-based query-by-example, WFST-based query-by-example, bottleneck features, keyword spotting

Autoři

TEJEDOR, J.; FAPŠO, M.; SZŐKE, I.; ČERNOCKÝ, J.; GRÉZL, F.

Rok RIV

2012

Vydáno

31. 8. 2012

Nakladatel

Association for Computing Machinery

Místo

New York

ISSN

1046-8188

Periodikum

ACM TRANSACTIONS ON INFORMATION SYSTEMS

Ročník

2012

Číslo

30

Stát

Spojené státy americké

Strany od

1

Strany do

34

Strany počet

34

URL

http://dl.acm.org/citation.cfm?id=2328971&CFID=187707319&CFTOKEN=67886685

BibTex

@article{BUT97057,
  author="Javier {Tejedor} and Michal {Fapšo} and Igor {Szőke} and Jan {Černocký} and František {Grézl}",
  title="Comparison of methods for language-dependent and language-independent query-by-example spoken term detection",
  journal="ACM TRANSACTIONS ON INFORMATION SYSTEMS",
  year="2012",
  volume="2012",
  number="30",
  pages="1--34",
  doi="10.1145/2328967.2328971",
  issn="1046-8188",
  url="http://dl.acm.org/citation.cfm?id=2328971&CFID=187707319&CFTOKEN=67886685"
}