Result Details

Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup

KOMBRINK, S.; MIKOLOV, T. Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup. Proceedings of the 17th Conference STUDENT EEICT 2011. Volume 3. Brno: Brno University of Technology, 2011. p. 527-531. ISBN: 978-80-214-4273-3.
Type
conference paper
Language
English
Authors
Kombrink Stefan, Dipl.-Linguist., DCGM (FIT)
Mikolov Tomáš, Ing., Ph.D., DCGM (FIT)
Abstract

This paper is on Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup.

Keywords

automatic speech recognition, language modeling, recurrent neural networks

URL
Annotation

In this paper we use recurrent neural network (RNN) based language models to improve our 2009 English meeting recognizer originated from the AMI/AMIDA project, which to date was the most advanced speech recognition setup of the Speech@FIT. On the baseline setup using the original language models we decrease word error rate (WER) from 20.3% to 19.1%. When language models in the system are replaced by models trained on a tiny subset of the original language model data, WER drops from 22.2% to 20.4%. Adding data sampled from two RNN models for language model training improves the overall system, yielding the performance of the original baseline (20.2%).

Published
2011
Pages
527–531
Proceedings
Proceedings of the 17th Conference STUDENT EEICT 2011
Series
Volume 3
Conference
Student EEICT 2011
ISBN
978-80-214-4273-3
Publisher
Brno University of Technology
Place
Brno
BibTeX 
@inproceedings{BUT91275,
  author="Stefan {Kombrink} and Tomáš {Mikolov}",
  title="Recurrent Neural Network Language Modeling Applied to the Brno AMI/AMIDA 2009 Meeting Recognizer Setup",
  booktitle="Proceedings of the 17th Conference STUDENT EEICT 2011",
  year="2011",
  series="Volume 3",
  pages="527--531",
  publisher="Brno University of Technology",
  address="Brno",
  isbn="978-80-214-4273-3",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/kombrink_eeict2011_volume3_527.pdf"
}
Projects
DIRAC - Detection and Identification of Rare Audio-visual Cues, MŠMT, Šestý rámcový program Evropského společenství pro výzkum, technický rozvoj a demonstrační činnosti, 027787, start: 2006-01-01, end: 2010-12-31, completed
Recognition and presentation of multimedia data, BUT, Vnitřní projekty VUT, FIT-S-10-2, 2010, start: 2010-04-01, end: 2010-12-31, 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