Title:
|
Deep belief networks for i-vector based speaker recognition
|
Author:
|
Ghahabi Esfahani, Omid; Hernando Pericás, Francisco Javier
|
Other authors:
|
Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions; Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
Abstract:
|
The use of Deep Belief Networks (DBNs) is proposed in this paper to model discriminatively target and impostor i-vectors in a speaker verification task. The authors propose to adapt the network parameters of each speaker from a background model, which will be referred to as Universal DBN (UDBN). It is also suggested to backpropagate class errors up to only one layer for few iterations before to train the network. Additionally, an impostor selection method is introduced which helps the DBN to outperform the cosine distance classifier. The evaluation is performed on the core test condition of the NIST SRE 2006 corpora, and it is shown that 10% and 8% relative improvements of EER and minDCF can be achieved, respectively. |
Abstract:
|
Peer Reviewed |
Subject(s):
|
-Àrees temàtiques de la UPC::Enginyeria de la telecomunicació -Àrees temàtiques de la UPC::Informàtica -Neural networks (Computer science) -Deep belief network -i-vector -Neural network -Speaker recognition -Xarxes neuronals (Informàtica) |
Rights:
|
|
Document type:
|
Article - Published version Conference Object |
Published by:
|
Institute of Electrical and Electronics Engineers (IEEE)
|
Share:
|
|