Detail publikace

Fast Approximate Spoken Term Detection from Sequence of Phonemes

PINTO, J. SZŐKE, I. PRASANNA, S. HEŘMANSKÝ, H.

Originální název

Fast Approximate Spoken Term Detection from Sequence of Phonemes

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

We investigate the detection of spoken terms in conversa- tional speech using phoneme recognition with the objective of achieving smaller index size as well as faster search speed. Speech is processed and indexed as a sequence of one best phoneme sequence. We propose the use of a probabilistic pronunciation model for the search term to compensate for the errors in the recognition of phonemes. This model is de- rived using the pronunciation of the word and the phoneme confusion matrix. Experiments are performed on the con- versational telephone speech database distributed by NIST for the 2006 spoken term detection. We achieve about 1500 times smaller index size and 14 times faster search speed compared to the system using phoneme lattices, at the cost of relatively lower detection performance.

Klíčová slova

Spoken term detection, probabilistic pronunciation model, phoneme recognition, confusion matrix

Autoři

PINTO, J.; SZŐKE, I.; PRASANNA, S.; HEŘMANSKÝ, H.

Rok RIV

2008

Vydáno

24. 7. 2008

Nakladatel

Association for Computing Machinery

Místo

Singapore

ISBN

978-90-365-2697-5

Kniha

The 31st Annual International ACM SIGIR Conference 20-24 July 2008, Singapore

Strany od

28

Strany do

33

Strany počet

8

BibTex

@inproceedings{BUT32585,
  author="Joel {Pinto} and Igor {Szőke} and S.R.M. {Prasanna} and Hynek {Heřmanský}",
  title="Fast Approximate Spoken Term Detection from Sequence of Phonemes",
  booktitle="The 31st Annual International ACM SIGIR Conference 20-24 July 2008, Singapore",
  year="2008",
  pages="28--33",
  publisher="Association for Computing Machinery",
  address="Singapore",
  isbn="978-90-365-2697-5"
}