Memorias de investigación
Communications at congresses:
Phonotactic Language Recognition using i-vectors and Phoneme Posteriogram Counts
Year:2012

Research Areas
  • Electronic technology and of the communications,
  • Electric engineers, electronic and automatic (eil)

Information
Abstract
This paper describes a novel approach to phonotactic LID, where instead of using soft-counts based on phoneme lattices, we use posteriogram to obtain n-gram counts. The high-dimensional vectors of counts are reduced to low-dimensional units for which we adapted the commonly used term i-vectors. The reduction is based on multinomial subspace modeling and is designed to work in the total-variability space. The proposed technique was tested on the NIST 2009 LRE set with better results to a system based on using soft-counts (Cavg on 30s: 3.15% vs 3.43%), and with very good results when fused with an acoustic i-vector LID system (Cavg on 30s acoustic 2.4% vs 1.25%). The proposed technique is also compared with another low dimensional projection system based on PCA. In comparison with the original soft-counts, the proposed technique provides better results, reduces the problems due to sparse counts, and avoids the process of using pruning techniques when creating the lattices.
International
Si
Congress
InterSpeech 2012, 13th Annual Conference of the International Speech Communication Association
960
Place
Portland, Oregon
Reviewers
Si
ISBN/ISSN
1990-9772
Start Date
09/09/2012
End Date
13/09/2012
From page
1
To page
4
InterSpeech 2012, 13th Annual Conference of the International Speech Communication Association
Participants
  • Autor: Luis Fernando D'Haro Enriquez UPM
  • Autor: Ondrej Glembek 2Brno University of Technology, Speech@FIT group and IT4I Center of Excellence, Czech Republic
  • Autor: Oldrich Plchot 2Brno University of Technology, Speech@FIT group and IT4I Center of Excellence, Czech Republic
  • Autor: Pavel Matejka 2Brno University of Technology, Speech@FIT group and IT4I Center of Excellence, Czech Republic
  • Autor: Mehdi Soufifar 2Brno University of Technology, Speech@FIT group and IT4I Center of Excellence, Czech Republic
  • Autor: Ricardo de Cordoba Herralde UPM
  • Autor: Jan Cernocký 2Brno University of Technology, Speech@FIT group and IT4I Center of Excellence, Czech Republic

Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Tecnología del Habla
  • Departamento: Ingeniería Electrónica