Recently, self-supervised learning (SSL) has demonstrated strong performance in speaker recognition, even if the pre-training objective is designed for speech recognition. In this paper, we study which factor leads to the success of self-supervised learning on speaker-related tasks, e.g. speaker verification (SV), through a series of carefully designed experiments. Our empirical results on the Voxceleb-1 dataset suggest that the benefit of SSL to SV task is from a combination of mask speech prediction loss, data scale, and model size, while the SSL quantizer has a minor impact. We further employ the integrated gradients attribution method and loss landscape visualization to understand the effectiveness of self-supervised learning for speaker recognition performance.
@article{arxiv.2204.12765,
title = {Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?},
author = {Sanyuan Chen and Yu Wu and Chengyi Wang and Shujie Liu and Zhuo Chen and Peidong Wang and Gang Liu and Jinyu Li and Jian Wu and Xiangzhan Yu and Furu Wei},
journal= {arXiv preprint arXiv:2204.12765},
year = {2022}
}