Speaker embeddings become growing popular in the text-independent speaker
verification task. In this paper, we propose two improvements during the
training stage. The improvements are both based on triplet cause the training
stage and the evaluation stage of the baseline x-vector system focus on
different aims. Firstly, we introduce triplet loss for optimizing the Euclidean
distances between embeddings while minimizing the multi-class cross entropy
loss. Secondly, we design an embedding similarity measurement network for
controlling the similarity between the two selected embeddings. We further
jointly train the two new methods with the original network and achieve
state-of-the-art. The multi-task training synergies are shown with a 9%
reduction equal error rate (EER) and detected cost function (DCF) on the 2016
NIST Speaker Recognition Evaluation (SRE) Test Set.

本文介绍了两种在培训阶段优化说话人嵌入的方法：使用三元组损失来优化嵌入之间的欧几里德距离并减少多类交叉熵损失，以及设计一种嵌入相似度测量网络来控制选定嵌入之间的相似度。将两个新方法与原始网络联合培训，实现了最先进的结果，对 2016 年 NIST 说话人识别评估测试集的等误差率（EER）和检测成本函数（DCF）分别降低了 9％。