Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning
arXiv:2207.05506 · doi:10.21437/Interspeech.2022-802
Abstract
State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to the amount of data available today. In this study, we explore self-supervised learning for speaker verification by learning representations directly from raw audio. The objective is to produce robust speaker embeddings that have small intra-speaker and large inter-speaker variance. Our approach is based on recent information maximization learning frameworks and an intensive data augmentation pre-processing step. We evaluate the ability of these methods to work without contrastive samples before showing that they achieve better performance when combined with a contrastive loss. Furthermore, we conduct experiments to show that our method reaches competitive results compared to existing techniques and can get better performances compared to a supervised baseline when fine-tuned with a small portion of labeled data.
arXiv commentaccepted to INTERSPEECH 2022
References in corpus (9)
- A Simple Framework for Contrastive Learning of Visual Representations
- Representation Learning with Contrastive Predictive Coding
- Bootstrap your own latent: A new approach to self-supervised Learning
- VoxCeleb: a large-scale speaker identification dataset
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
- In defence of metric learning for speaker recognition
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics