Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yafeng, Zheng, Siqi, Wang, Hui, Cheng, Luyao, Chen, Qian, Zhang, Shiliang, Wang, Wen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910762247651328
author Chen, Yafeng
Zheng, Siqi
Wang, Hui
Cheng, Luyao
Chen, Qian
Zhang, Shiliang
Wang, Wen
author_facet Chen, Yafeng
Zheng, Siqi
Wang, Hui
Cheng, Luyao
Chen, Qian
Zhang, Shiliang
Wang, Wen
contents Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new self-supervised speaker verification approach, Self-Distillation Prototypes Network (SDPN), which effectively facilitates self-supervised speaker representation learning. SDPN assigns the representation of the augmented views of an utterance to the same prototypes as the representation of the original view, thereby enabling effective knowledge transfer between the views. Originally, due to the lack of negative pairs in the SDPN training process, the network tends to align positive pairs very closely in the embedding space, a phenomenon known as model collapse. To alleviate this problem, we introduce a diversity regularization term to embeddings in SDPN. Comprehensive experiments on the VoxCeleb datasets demonstrate the superiority of SDPN in self-supervised speaker verification. SDPN sets a new state-of-the-art on the VoxCeleb1 speaker verification evaluation benchmark, achieving Equal Error Rate 1.80%, 1.99%, and 3.62% for trial VoxCeleb1-O, VoxCeleb1-E and VoxCeleb1-H respectively, without using any speaker labels in training.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11169
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
Chen, Yafeng
Zheng, Siqi
Wang, Hui
Cheng, Luyao
Chen, Qian
Zhang, Shiliang
Wang, Wen
Audio and Speech Processing
Sound
Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new self-supervised speaker verification approach, Self-Distillation Prototypes Network (SDPN), which effectively facilitates self-supervised speaker representation learning. SDPN assigns the representation of the augmented views of an utterance to the same prototypes as the representation of the original view, thereby enabling effective knowledge transfer between the views. Originally, due to the lack of negative pairs in the SDPN training process, the network tends to align positive pairs very closely in the embedding space, a phenomenon known as model collapse. To alleviate this problem, we introduce a diversity regularization term to embeddings in SDPN. Comprehensive experiments on the VoxCeleb datasets demonstrate the superiority of SDPN in self-supervised speaker verification. SDPN sets a new state-of-the-art on the VoxCeleb1 speaker verification evaluation benchmark, achieving Equal Error Rate 1.80%, 1.99%, and 3.62% for trial VoxCeleb1-O, VoxCeleb1-E and VoxCeleb1-H respectively, without using any speaker labels in training.
title Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2406.11169