Efficient two-stage speaker identification based on universal background models
| dc.contributor.author | Billeb, Stefan | |
| dc.contributor.author | Rathgeb, Christian | |
| dc.contributor.author | Buschbeck, Michael | |
| dc.contributor.author | Reininger, Herbert | |
| dc.contributor.author | Kasper, Klaus | |
| dc.contributor.editor | Brömme, Arslan | |
| dc.contributor.editor | Busch, Christoph | |
| dc.date.accessioned | 2017-07-26T10:54:16Z | |
| dc.date.available | 2017-07-26T10:54:16Z | |
| dc.date.issued | 2014 | |
| dc.description.abstract | Conventional speaker identification systems are already field-proven with respect to recognition accuracy. Since any biometric identification requires exhaustive 1 : N comparisons for identifying a biometric probe, comparison time frequently dominates the overall computational workload, preventing the system from being executed in real-time. In this paper we propose a computational efficient two-stage speaker identification system based on Gaussian Mixture Model and Universal Background Model. Binarized voice biometric templates are utilized to pre-screen a large database and thereby reduce the required amount of full comparisons to a fraction of the total. Experimental evaluations demonstrate that the proposed system is capable of significantly accelerating the response-time of the system and, at the same time, identification performance is maintained, confirming the soundness of the scheme. | en |
| dc.identifier.isbn | 978-3-88579-624-4 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | BIOSIG 2014 | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-230 | |
| dc.title | Efficient two-stage speaker identification based on universal background models | en |
| dc.type | Text/Conference Paper | |
| gi.citation.endPage | 156 | |
| gi.citation.publisherPlace | Bonn | |
| gi.citation.startPage | 145 | |
| gi.conference.date | 10.-12. September 2014 | |
| gi.conference.location | Darmstadt |
Dateien
Originalbündel
1 - 1 von 1