Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Global impostor selection for DBNs in multi-session i-vector speaker recognition

Autor
Ghahabi, O.; Hernando, J.
Tipus d'activitat
Article en revista
Revista
Lecture notes in computer science
Data de publicació
2014-11-19
Volum
LNAI 8854
Pàgina inicial
89
Pàgina final
98
DOI
https://doi.org/10.1007/978-3-319-13623-3_10 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/27397 Obrir en finestra nova
URL
http://link.springer.com/chapter/10.1007%2F978-3-319-13623-3_10 Obrir en finestra nova
Resum
An effective global impostor selection method is proposed in this paper for discriminative Deep Belief Networks (DBN) in the context of a multi-session i-vector based speaker recognition. The proposed method is an iterative process in which in each iteration the whole impostor i-vector dataset is divided randomly into two subsets. The impostors in one subset which are closer to each impostor in another subset are selected and impostor frequencies are computed. At the end, those impostors with hi...
Citació
Ghahabi, O.; Hernando, J. Global impostor selection for DBNs in multi-session i-vector speaker recognition. "Lecture notes in computer science", 19 Novembre 2014, vol. LNAI 8854, p. 89-98.
Paraules clau
Deep belief network, Impostor selection, NIST i-vector challenge, Speaker recognition
Grup de recerca
IDEAI-UPC Intelligent Data Science and Artificial Intelligence
TALP - Centre de Tecnologies i Aplicacions del Llenguatge i la Parla
VEU - Grup de Tractament de la Parla

Participants