학술논문
Discriminative Speaker Representation Via Contrastive Learning with Class-Aware Attention in Angular Space
Document Type
Conference
Author
Source
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2023 - 2023 IEEE International Conference on. :1-5 Jun, 2023
Subject
Language
ISSN
2379-190X
Abstract
The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning. To overcome the first challenge, we propose a contrastive learning SV framework incorporating an additive angular margin into the supervised contrastive loss in which the margin improves the speaker representation’s discrimination ability. For the second challenge, we introduce a class-aware attention mechanism through which hard negative samples contribute less significantly to the supervised contrastive loss. We also employed gradient-based multi-objective optimization to balance the classification and contrastive loss. Experimental results on CN-Celeb and Voxceleb1 show that this new learning objective can cause the encoder to find an embedding space that exhibits great speaker discrimination across languages.