Result Details

Approaches to automatic LEXICON learning with limited training examples

GOEL, N.; THOMAS, S.; AGARWAL, M.; AKYAZI, P.; BURGET, L.; FENG, K.; GHOSHAL, A.; GLEMBEK, O.; KARAFIÁT, M.; POVEY, D.; RASTROW, A.; ROSE, R.; SCHWARZ, P. Approaches to automatic LEXICON learning with limited training examples. Proc. International Conference on Acoustics, Speech, and Signal Processing. Proc. International Conference on Acoustics, Speech, and Signal Processing. Dallas: IEEE Signal Processing Society, 2010. no. 3, p. 5094-5097. ISBN: 978-1-4244-4296-6. ISSN: 1520-6149.
Type
conference paper
Language
English
Authors
Goel Nagendra
Thomas Samuel
Agarwal Mohit
Akyazi Pinar
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Feng Kai
Ghoshal Arnab
Glembek Ondřej, Ing., Ph.D., DCGM (FIT)
Karafiát Martin, Ing., Ph.D., DCGM (FIT)
Povey Daniel
Rastrow Ariya
Rose Richard
Schwarz Petr, Ing., Ph.D., DCGM (FIT)
Abstract

The paper is on approaches to automatic lexicon learning with limited training examples. We use a combination of lexicon learning techniques.

Keywords

Lexicon Learning, LVCSR

URL
Annotation

Preparation of a lexicon for speech recognition systems can be a significant effort in languages where the written form is not exactly phonetic. On the other hand, in languages where the written form is quite phonetic, some common words are often mispronounced. In this paper, we use a combination of lexicon learning techniques to explore whether a lexicon can be learned when only a small lexicon is available for boot-strapping. We discover that for a phonetic language such as Spanish, it is possible to do that better than what is possible from generic rules or hand-crafted pronunciations. For a more complex language such as English, we find that it is still possible but with some loss of accuracy.

Published
2010
Pages
5094–5097
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
ISBN
978-1-4244-4296-6
Publisher
IEEE Signal Processing Society
Place
Dallas
BibTeX
@inproceedings{BUT37050,
  author="Nagendra {Goel} and Samuel {Thomas} and Mohit {Agarwal} and Pinar {Akyazi} and Lukáš {Burget} and Kai {Feng} and Arnab {Ghoshal} and Ondřej {Glembek} and Martin {Karafiát} and Daniel {Povey} and Ariya {Rastrow} and Richard {Rose} and Petr {Schwarz}",
  title="Approaches to automatic LEXICON learning with limited training examples",
  booktitle="Proc. International Conference on Acoustics, Speech, and Signal Processing",
  year="2010",
  journal="Proc. International Conference on Acoustics, Speech, and Signal Processing",
  volume="2010",
  number="3",
  pages="5094--5097",
  publisher="IEEE Signal Processing Society",
  address="Dallas",
  isbn="978-1-4244-4296-6",
  issn="1520-6149",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2010/goel_icassp2010_0005094.pdf"
}
Projects
Multilingual recognition and search in speech for electronic dictionaries, MPO, TIP, FR-TI1/034, start: 2009-09-01, end: 2013-08-31, completed
Research groups
Departments
Back to top