Memorias de investigación
Communications at congresses:
Applying feature reduction analysis to a PPRLM-multiple Gaussian language identification system
Year:2008

Research Areas
  • Artificial intelligence,
  • Electronics engineering

Information
Abstract
This paper presents the application of a feature selection technique such as LDA to a language identification (LID) system. The baseline system consists of a PPRLM module followed by a multiple-Gaussian classifier. This classifier makes use of acoustic scores and duration features of each input utterance. We applied a dimension reduction of the feature space in order to achieve a faster and easier-trainable system. We imputed missing values of our vectors before projecting them on the new space. Our experiments show a very low performance reduction due to the dimension reduction approach. Using a single dimension projection the error rates we have obtained are about 8.73% taking into account the 22 most significant features.
International
No
Congress
V Jornadas de Tecnología del Habla
960
Place
Bilbao
Reviewers
Si
ISBN/ISSN
978-84-9860-169-5
Start Date
12/11/2008
End Date
14/11/2008
From page
29
To page
32
Actas de V Jornadas de Tecnología del Habla
Participants

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