An iterative framework for self-supervised deep speaker representation learning

Abstract

In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing agreement between different segments within an utterance via a contrastive loss. Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding obtained from the previous speaker network and use the subsequent class assignments as pseudo labels to train a new DNN. Moreover, we iteratively train the speaker network with pseudo labels generated from the previous step to bootstrap the discriminative power of a DNN. Speaker verification experiments are conducted on the VoxCeleb dataset. The results show that our proposed iterative self-supervised learning framework outperformed previous works using self-supervision. The speaker network after 5 iterations obtains a 61% performance gain over the speaker embedding model trained with contrastive loss.

arXiv commentarXiv admin note: text overlap with arXiv:2010.12731

References in corpus (9)

• A Simple Framework for Contrastive Learning of Visual Representations
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• VoxCeleb2: Deep Speaker Recognition
• VoxCeleb: a large-scale speaker identification dataset
• In defence of metric learning for speaker recognition
• Regularizing Neural Networks by Penalizing Confident Output Distributions
• A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
• 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