Local Training for PLDA in Speaker Verification

TL;DR

This paper introduces a local training method for PLDA in speaker verification that uses inexpensive local labels to improve performance when global labels are scarce.

Contribution

It proposes a novel local training approach that leverages inexpensive local labels for PLDA adaptation, reducing the need for costly global labels.

Findings

Significant performance improvements with limited global labels

Effective use of local labels for PLDA training

Enhanced speaker verification accuracy

Abstract

PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labeled development data, which is highly expensive in most cases. A possible approach to mitigate the problem is various unsupervised adaptation methods, which use unlabeled data to adapt the PLDA scattering matrices to the target domain. In this paper, we present a new `local training' approach that utilizes inaccurate but much cheaper local labels to train the PLDA model. These local labels discriminate speakers within a single conversion only, and so are much easier to obtain compared to the normal `global labels'. Our experiments show that the proposed approach can deliver significant performance improvement, particularly with limited globally-labeled data.