Result Details

Independent Component Analysis and MLLR Transforms for Speaker Identification

CUMANI, S.; PLCHOT, O.; KARAFIÁT, M. Independent Component Analysis and MLLR Transforms for Speaker Identification. Proc. International Conference on Acoustics, Speech, and Signal P. Kyoto: IEEE Signal Processing Society, 2012. p. 4365-4368. ISBN: 978-1-4673-0044-5.
Type
conference paper
Language
English
Authors
Cumani Sandro, Ph.D.
Plchot Oldřich, Ing., Ph.D., DCGM (FIT)
Karafiát Martin, Ing., Ph.D., DCGM (FIT)
Abstract

This paper describes the use of of Independent Component Analysis (ICA) and Principal Component Analysis (PCA) techniques to reduce the dimensionality of high-level LVCSR features.

Keywords

Speaker Recognition, MLLR, ICA, PLDA,SVM

URL
Annotation

In this paper, we explore the use of Independent Component Analysis (ICA) and Principal Component Analysis (PCA) techniques to reduce the dimensionality of high-level LVCSR features and at the same time to enable modelling them with state-of-the-art techniques like Probabilistic Linear Discriminant Analysis or Pairwise Support Vector Machines (PSVM). The high-level features are the coefficients from Constrained Maximum-Likelihood Linear Regression (CMLLR) and Maximum-Likelihood Linear Regression (MLLR) transforms estimated in an Automatic Speech Recognition (ASR) system. We also compare a classical approach of modeling every speaker by a single SVM classifier with the recent state-of-the-art modelling techniques in Speaker Identification. We report performance of the systems and score-level combination with a current state-of-the-art acoustic i-vector system on the NIST SRE2010 dataset.

Published
2012
Pages
4365–4368
Proceedings
Proc. International Conference on Acoustics, Speech, and Signal P
Conference
The 37th International Conference on Acoustics, Speech, and Signal Processing
ISBN
978-1-4673-0044-5
Publisher
IEEE Signal Processing Society
Place
Kyoto
DOI
10.1109/ICASSP.2012.6288886
BibTeX 
@inproceedings{BUT91483,
  author="Sandro {Cumani} and Oldřich {Plchot} and Martin {Karafiát}",
  title="Independent Component Analysis and MLLR Transforms for Speaker Identification",
  booktitle="Proc. International Conference on Acoustics, Speech, and Signal P",
  year="2012",
  pages="4365--4368",
  publisher="IEEE Signal Processing Society",
  address="Kyoto",
  doi="10.1109/ICASSP.2012.6288886",
  isbn="978-1-4673-0044-5",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2012/cumani_icassp2012_0004365.pdf"
}
Projects
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
Technologies of speech processing for efficient human-machine communication, TAČR, Program aplikovaného výzkumu a experimentálního vývoje ALFA, TA01011328, start: 2011-01-01, end: 2014-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top