A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition

TL;DR

This paper introduces a flexible domain adaptation framework for PLDA in speaker recognition, incorporating new correlation-alignment and covariance regularization techniques that improve robustness and performance across domains.

Contribution

It presents a generalized domain adaptation framework for PLDA, including novel correlation-alignment-based interpolation and covariance regularization methods.

Findings

Correlation-alignment-based interpolation reduces minCprimary by up to 30.5%.

Regularization enhances robustness to interpolation weight variations.

Performance surpasses traditional methods in domain adaptation scenarios.

Abstract

This paper proposes a generalized framework for domain adaptation of Probabilistic Linear Discriminant Analysis (PLDA) in speaker recognition. It not only includes several existing supervised and unsupervised domain adaptation methods but also makes possible more flexible usage of available data in different domains. In particular, we introduce here the two new techniques described below. (1) Correlation-alignment-based interpolation and (2) covariance regularization. The proposed correlation-alignment-based interpolation method decreases minCprimary up to 30.5% as compared with that from an out-of-domain PLDA model before adaptation, and minCprimary is also 5.5% lower than with a conventional linear interpolation method with optimal interpolation weights. Further, the proposed regularization technique ensures robustness in interpolations w.r.t. varying interpolation weights, which in practice is essential.