Self-Supervised Speaker Recognition with Loss-Gated Learning

Page view(s)
68
Checked on Feb 21, 2025
Self-Supervised Speaker Recognition with Loss-Gated Learning
Title:
Self-Supervised Speaker Recognition with Loss-Gated Learning
Journal Title:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Keywords:
Publication Date:
27 April 2022
Citation:
Tao, R., Aik Lee, K., Kumar Das, R., Hautamaki, V., & Li, H. (2022). Self-Supervised Speaker Recognition with Loss-Gated Learning. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp43922.2022.9747162
Abstract:
In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals. It is a known fact that a speaker recognition model doesn’t always benefit from pseudo labels due to their unreliability. In this work, we observe that a speaker recognition network tends to model the data with reliable labels faster than those with unreliable labels. This motivates us to study a loss-gated learning (LGL) strategy, which extracts the reliable labels through the fitting ability of the neural network during training. With the proposed LGL, our speaker recognition model obtains a 46:3% performance gain over the system without it. Further, the proposed self-supervised speaker recognition with LGL trained on the VoxCeleb2 dataset without any labels achieves an equal error rate of 1:66% on the VoxCeleb1 original test set.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
ISBN:
978-1-6654-0541-6
Files uploaded: