A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition
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 from an out-of-domain PLDA model before adaptation, and minCprimary is also 5.5 interpolation weights. Further, the proposed regularization technique ensures robustness in interpolations w.r.t. varying interpolation weights, which in practice is essential.
READ FULL TEXT