Result Details

Discrimininative training of narrow band - wide band adaptated systems for meeting recognition

KARAFIÁT, M.; BURGET, L.; HAIN, T.; ČERNOCKÝ, J. Discrimininative training of narrow band - wide band adaptated systems for meeting recognition. Proc. Interspeech 2008. Proceedings of Interspeech. Brisbane: International Speech Communication Association, 2008. no. 9, p. 1-4. ISSN: 1990-9772.
Type
conference paper
Language
English
Authors
Karafiát Martin, Ing., Ph.D., FIT (FIT), DCGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Hain Thomas
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Abstract

The paper is on Discrimininative training of narrow band - wide band adaptated systems for meeting recognition

Keywords

speech recognition

URL
Annotation

The amount of training data has a crucial effect on the accuracy of HMM based meeting recognition systems. One of the largest collections of speech data is conversational telephone speech which was found to match speech in meetings well. However it is naturally recorded with limited bandwidth. In previous work we presented a scheme that allows to transform wide-band meeting data into the same space for improved model training. In this paper we focused on integration of discriminative adaptation into this scheme. This integration is not straightforward and we present the complexity of this process. The models are tested on the NIST RT'05 meeting evaluation where a relative reduction in word error rate of 5.6% against non-adapted meeting system was achieved.

Published
2008
Pages
1–4
Journal
Proceedings of Interspeech, no. 9, ISSN 1990-9772
Proceedings
Proc. Interspeech 2008
Conference
Interspeech Conference
Publisher
International Speech Communication Association
Place
Brisbane
BibTeX 
@inproceedings{BUT33437,
  author="Martin {Karafiát} and Lukáš {Burget} and Thomas {Hain} and Jan {Černocký}",
  title="Discrimininative training of narrow band - wide band adaptated systems for meeting recognition",
  booktitle="Proc. Interspeech 2008",
  year="2008",
  journal="Proceedings of Interspeech",
  number="9",
  pages="1--4",
  publisher="International Speech Communication Association",
  address="Brisbane",
  issn="1990-9772",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2008/karafiat_is2008.pdf"
}
Projects
Interactive Keyword Detector, GACR, Postdoktorandské granty, GP102/06/P383, start: 2006-01-01, end: 2008-12-31, completed
Security-Oriented Research in Information Technology, MŠMT, Institucionální prostředky SR ČR (např. VZ, VC), MSM0021630528, start: 2007-01-01, end: 2013-12-31, running
Speech Recognition under Real-World Conditions, GACR, Standardní projekty, GA102/08/0707, start: 2008-01-01, end: 2011-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top