Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification

Abstract

In this paper, we propose self-supervised speaker representation learning strategies, which comprise of a bootstrap equilibrium speaker representation learning in the front-end and an uncertainty-aware probabilistic speaker embedding training in the back-end. In the front-end stage, we learn the speaker representations via the bootstrap training scheme with the uniformity regularization term. In the back-end stage, the probabilistic speaker embeddings are estimated by maximizing the mutual likelihood score between the speech samples belonging to the same speaker, which provide not only speaker representations but also data uncertainty. Experimental results show that the proposed bootstrap equilibrium training strategy can effectively help learn the speaker representations and outperforms the conventional methods based on contrastive learning. Also, we demonstrate that the integrated two-stage framework further improves the speaker verification performance on the VoxCeleb1 test set in terms of EER and MinDCF.

arXiv commentAccepted by IEEE Access

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• A Simple Framework for Contrastive Learning of Visual Representations
• Representation Learning with Contrastive Predictive Coding
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Bootstrap your own latent: A new approach to self-supervised Learning
• Instance Normalization: The Missing Ingredient for Fast Stylization
• VoxCeleb2: Deep Speaker Recognition
• VoxCeleb: a large-scale speaker identification dataset
• Self-supervised Learning: Generative or Contrastive
• Contrastive Representation Learning: A Framework and Review
• What Makes for Good Views for Contrastive Learning?
• Attentive Statistics Pooling for Deep Speaker Embedding
• In defence of metric learning for speaker recognition
• Universally optimal distribution of points on spheres
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• Word Representations via Gaussian Embedding
• Modeling Uncertainty with Hedged Instance Embedding
• Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics
• Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
• Seeing voices and hearing voices: learning discriminative embeddings using cross-modal self-supervision
• Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition
• Fast and Reliable Probabilistic Face Embeddings in the Wild