An Iterative Framework For Self-supervised Deep Speaker Representation Learning
2020 · Danwei Cai, Weiqing Wang, Ming Li
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 embeddin
Authors
(none)
Tags
Stats
Related papers
- The Dku-dukeece System For The Self-supervision Speaker Verification Task Of The 2021 Voxceleb Speaker Recognition Challenge (2021)0.00
- Curriculum Learning For Self-supervised Speaker Verification (2022)8.09
- Self-supervised Reflective Learning Through Self-distillation And Online Clustering For Speaker Representation Learning (2024)2.26
- Self-distillation Prototypes Network: Learning Robust Speaker Representations Without Supervision (2023)4.52
- Deep Self-supervised Hierarchical Clustering For Speaker Diarization (2020)5.24
- Self-supervised Speaker Verification With Simple Siamese Network And Self-supervised Regularization (2021)10.85
- Pushing The Limits Of Self-supervised Speaker Verification Using Regularized Distillation Framework (2022)17.00
- Augmentation Adversarial Training For Self-supervised Speaker Recognition (2020)0.00