An analysis framework of two-level sampling subspace for speaker verification

Na Li, Xiangyang Zeng, Zhifeng Li, Weiwu Jiang, Yu Qiao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Using high-dimensional Joint Factor Analysis (JFA) speaker supervectors for the Fishervoice based subspace analysis suffers high computational complexity problem in the model training process. To address this problem, we propose a two-level sampling subspace framework. For the first level of this framework, partial mean vectors are selected from the JFA speaker supervector to form a low-dimensional feature vector. For the second level, PCA is first applied to perform dimension reduction for the feature vector. Several classifiers are then constructed on a collection of random subspaces generated by randomly sampling the reduced feature space. Finally, all classifiers are fused to obtain the final decision. Experimental results on NIST08 show that the proposed framework improves the performance of JFA and Fishervoice by a relative decrease of 13.8% and 7.2% respectively on EER. The minDCF is reduced to 2.19 by using the new model.

Original languageEnglish
Title of host publication2013 IEEE International Conference of IEEE Region 10, IEEE TENCON 2013 - Conference Proceedings
DOIs
StatePublished - 2013
Event2013 IEEE International Conference of IEEE Region 10, IEEE TENCON 2013 - Xi'an, Shaanxi, China
Duration: 22 Oct 201325 Oct 2013

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Conference

Conference2013 IEEE International Conference of IEEE Region 10, IEEE TENCON 2013
Country/TerritoryChina
CityXi'an, Shaanxi
Period22/10/1325/10/13

Keywords

  • Fishervoice
  • randomly sampling
  • subspace analysis
  • supervector

Fingerprint

Dive into the research topics of 'An analysis framework of two-level sampling subspace for speaker verification'. Together they form a unique fingerprint.

Cite this