HiLAM-aligned kernel discriminant analysis for text-dependent speaker verification

作者：

Highlights：

• The main highlights of the work may be stated as follows.

• Kernel Discriminant Analysis for Text-dependent speaker verification task.

• A new speaker-text class is defined using Hierarchical multi-Layer Acoustic Model.

• Integration of new speaker-text class definition with i-vector and xvector systems.

• The systems have been validated on Part 1 of the RSR2015 database.

摘要

•The main highlights of the work may be stated as follows.•Kernel Discriminant Analysis for Text-dependent speaker verification task.•A new speaker-text class is defined using Hierarchical multi-Layer Acoustic Model.•Integration of new speaker-text class definition with i-vector and xvector systems.•The systems have been validated on Part 1 of the RSR2015 database.

论文关键词：Text-dependent speaker verification,Kernel Discriminant Analysis,HiLAM,Online i-vector/PLDA,X-vector

论文评审过程：Received 28 September 2019, Revised 20 April 2021, Accepted 22 May 2021, Available online 29 May 2021, Version of Record 3 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115281