Publication Details

Subword-based spoken term detection in audio course lectures

ROSE Richard, NOROUZIAN Atta, REDDY Aarthi, COY Andre, GUPTA Vishwa and KARAFIÁT Martin. Subword-based spoken term detection in audio course lectures. In: Proc. International Conference on Acoustics, Speech, and Signal Processing. Dallas: IEEE Signal Processing Society, 2010, pp. 5282-5285. ISBN 978-1-4244-4296-6. ISSN 1520-6149.
Czech title
Pod-slovní jednotky pro detekci klíčových frází v audiozáznamech přednášek
Type
conference paper
Language
english
Authors
Rose Richard (MCGILL)
Norouzian Atta (MCGILL)
Reddy Aarthi (MCGILL)
Coy Andre (MCGILL)
Gupta Vishwa (CRIM)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords

Speech recognition, spoken term detection

Abstract

This paper regards the subword-based spoken term detection in audio course lectures. It investigates spoken term dection (STD) from audio recordings.

Annotation

This paper investigates spoken term detection (STD) from audio recordings of course lectures obtained from an existing media repository. STD is performed from word lattices generated offline using an automatic speech recognition (ASR) system configured from a meetings domain. An efficient STD approach is presented where lattice paths which are likely to contain search terms are identified and an efficient phone based distance is used to detect the occurrence of search terms in phonetic expansions of promising lattice paths. STD and ASR results are reported for both in-vocabulary (IV) and outof- vocabulary (OOV) search terms in this lecture speech domain.

Published
2010
Pages
5282-5285
Journal
Proc. International Conference on Acoustics, Speech, and Signal Processing, vol. 2010, no. 3, ISSN 1520-6149
Proceedings
Proc. International Conference on Acoustics, Speech, and Signal Processing
Conference
International Conference on Acoustics, Speech, and Signal Processing 2010, Dallas, US
ISBN
978-1-4244-4296-6
Publisher
IEEE Signal Processing Society
Place
Dallas, US
BibTeX 
@INPROCEEDINGS{FITPUB9312,
   author = "Richard Rose and Atta Norouzian and Aarthi Reddy and Andre Coy and Vishwa Gupta and Martin Karafi\'{a}t",
   title = "Subword-based spoken term detection in audio course lectures",
   pages = "5282--5285",
   booktitle = "Proc. International Conference on Acoustics, Speech, and Signal Processing",
   journal = "Proc. International Conference on Acoustics, Speech, and Signal Processing",
   volume = 2010,
   number = 3,
   year = 2010,
   location = "Dallas, US",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-4244-4296-6",
   ISSN = "1520-6149",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9312"
}
Back to top