Discriminative Speaker Representation Via Contrastive Learning with Class-Aware Attention in Angular Space
Authors:
- 4 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
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.Keywords
This publication has 24 references indexed in Scilit:
- Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification2021
- ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification2020
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition2019
- ArcFace: Additive Angular Margin Loss for Deep Face Recognition2019
- Unsupervised Feature Learning via Non-parametric Instance Discrimination2018
- Additive Margin Softmax for Face VerificationIEEE Signal Processing Letters, 2018
- Generalized End-to-End Loss for Speaker Verification2018
- Embedding Deep Metric for Person Re-identification: A Study Against Large Variations2016
- Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning with Humans in the Loop2016
- FaceNet: A unified embedding for face recognition and clustering2015