Mostra el registre d'ítem simple
Global impostor selection for DBNs in multi-session i-vector speaker recognition
dc.contributor.author | Ghahabi Esfahani, Omid |
dc.contributor.author | Hernando Pericás, Francisco Javier |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2015-04-16T16:30:47Z |
dc.date.created | 2014-11-19 |
dc.date.issued | 2014-11-19 |
dc.identifier.citation | 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. |
dc.identifier.issn | 0302-9743 |
dc.identifier.uri | http://hdl.handle.net/2117/27397 |
dc.description.abstract | 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 higher frequencies will be the global selected ones. They are then clustered and the centroids are considered as the final impostors for the DBN speaker models. The advantage of the proposed method is that in contrary to other similar approaches, only the background i-vector dataset is employed. The experimental results are performed on the NIST 2014 i-vector challenge dataset and it is shown that the proposed selection method improves the performance of the DBN-based system in terms of minDCF by 7% and the whole system outperforms the baseline in the challenge by more than 22% relative improvement. |
dc.format.extent | 10 p. |
dc.language.iso | eng |
dc.rights | Attribution-NonCommercial-NoDerivs 3.0 Spain |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic |
dc.subject | Àrees temàtiques de la UPC::Informàtica |
dc.subject.lcsh | Automatic speech recognition |
dc.subject.other | Speaker recognition |
dc.subject.other | Deep belief network |
dc.subject.other | Impostor selection |
dc.subject.other | NIST i-vector challenge |
dc.title | Global impostor selection for DBNs in multi-session i-vector speaker recognition |
dc.type | Article |
dc.subject.lemac | Reconeixement automàtic de la parla |
dc.contributor.group | Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
dc.identifier.doi | 10.1007/978-3-319-13623-3_10 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | http://link.springer.com/chapter/10.1007%2F978-3-319-13623-3_10 |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 15429563 |
dc.description.version | Postprint (published version) |
dc.date.lift | 10000-01-01 |
local.citation.author | Ghahabi, O.; Hernando, J. |
local.citation.publicationName | Lecture notes in computer science |
local.citation.volume | LNAI 8854 |
local.citation.startingPage | 89 |
local.citation.endingPage | 98 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [172]
-
Articles de revista [2.526]