Squeezing Value Of Cross-Domain Labels: A Decoupled Scoring Approach For Speaker Verification

Domain mismatch is often occurred in real applications and causes serious performance reduction on speaker recognition systems. The common wisdom is to collect cross-domain data and train a multi-domain PLDA model, with the hope to learn a domain-independent speaker subspace. In this paper, we firstly present an empirical study to show that simply adding cross-domain data does not help performance in conditions with enroll-test mismatch. Careful analysis shows that this striking result is caused by the incoherent statistics between enroll and test conditions. Based on this analysis, we present a decoupled scoring approach that can maximally squeeze the value of cross-domain labels and obtain optimal verification scores in the enrollment-test mismatch condition. When the statistics are coherent, the new formulation falls back to the conventional PLDA. Experimental results on cross-channel test show that the proposed approach is highly effective and is a principal solution to domain mismatch.