Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition
arXiv:2006.04326
Abstract
This paper introduces a semi-supervised contrastive learning framework and its application to text-independent speaker verification. The proposed framework employs generalized contrastive loss (GCL). GCL unifies losses from two different learning frameworks, supervised metric learning and unsupervised contrastive learning, and thus it naturally determines the loss for semi-supervised learning. In experiments, we applied the proposed framework to text-independent speaker verification on the VoxCeleb dataset. We demonstrate that GCL enables the learning of speaker embeddings in three manners, supervised learning, semi-supervised learning, and unsupervised learning, without any changes in the definition of the loss function.
References in corpus (9)
- Prototypical Networks for Few-shot Learning
- VoxCeleb2: Deep Speaker Recognition
- VoxCeleb: a large-scale speaker identification dataset
- Improved Baselines with Momentum Contrastive Learning
- Learning deep representations by mutual information estimation and maximization
- ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
- Momentum Contrast for Unsupervised Visual Representation Learning
- In defence of metric learning for speaker recognition
- AutoSpeech: Neural Architecture Search for Speaker Recognition
Cited by in corpus (10)
- VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
- Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification
- Graph-based Label Propagation for Semi-Supervised Speaker Identification
- The IDLAB VoxCeleb Speaker Recognition Challenge 2020 System Description
- The DKU-DukeECE System for the Self-Supervision Speaker Verification Task of the 2021 VoxCeleb Speaker Recognition Challenge
- Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification
- An iterative framework for self-supervised deep speaker representation learning
- Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learning
- Unsupervised Representation Learning for Speaker Recognition via Contrastive Equilibrium Learning
- Momentum Contrast Speaker Representation Learning