English

Multi-task Metric Learning for Text-independent Speaker Verification

Audio and Speech Processing 2023-03-24 v2 Sound

Abstract

In this work, we introduce metric learning (ML) to enhance the deep embedding learning for text-independent speaker verification (SV). Specifically, the deep speaker embedding network is trained with conventional cross entropy loss and auxiliary pair-based ML loss function. For the auxiliary ML task, training samples of a mini-batch are first arranged into pairs, then positive and negative pairs are selected and weighted through their own and relative similarities, and finally the auxiliary ML loss is calculated by the similarity of the selected pairs. To evaluate the proposed method, we conduct experiments on the Speaker in the Wild (SITW) dataset. The results demonstrate the effectiveness of the proposed method.

Keywords

Cite

@article{arxiv.2010.10919,
  title  = {Multi-task Metric Learning for Text-independent Speaker Verification},
  author = {Yafeng Chen and Wu Guo and Jingjing Shi and Jiajun Qi and Tan Liu},
  journal= {arXiv preprint arXiv:2010.10919},
  year   = {2023}
}

Comments

Not a particularly high-quality work, so we request withdrawal

R2 v1 2026-06-23T19:31:10.504Z