paper-with-me

Papers

Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations

2024-04-23 · Theo Lepage, Reda Dehak

Self-Supervised Learning (SSL) frameworks became the standard for learning robust class representations by benefiting from large unlabeled datasets. For Speaker Verification (SV), most SSL systems rely on contrastive-based loss functions. We explore different ways to improve the performance of these techniques by revisiting the NT-Xent contrastive loss. Our main contribution is the definition of the NT-Xent-AM loss and the study of the importance of Additive Margin (AM) in SimCLR and MoCo SSL methods to further separate positive from negative pairs. Despite class collisions, we show that AM enhances the compactness of same-speaker embeddings and reduces the number of false negatives and false positives on SV. Additionally, we demonstrate the effectiveness of the symmetric contrastive loss, which provides more supervision for the SSL task. Implementing these two modifications to SimCLR improves performance and results in 7.85% EER on VoxCeleb1-O, outperforming other equivalent methods.

📄 PDF Abstract BibTeX arXiv:2404.14913

Code (1)

theolepage/sslsv 공식 구현 pytorch

Tasks

Self-Supervised LearningSpeaker Verification

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Bitcoin Customer Service Number +1-833-534-1729 설명 없음
Average Pooling 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
ColorJitter 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification

2023-06-06 · Theo Lepage, Reda Dehak

Most state-of-the-art self-supervised speaker verification systems rely on a contrastive-based objective function to learn speaker representations from unlabeled speech data. We explore different ways to improve the perf…

Speaker Verification

DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning

2023-09-21 · Thanh Nguyen, Trung Pham, Chaoning Zhang, Tung Luu 외

Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has achieved comparable or better performance w…

Contrastive LearningDiversitySelf-Supervised Learning

EqCo: Equivalent Rules for Self-supervised Contrastive Learning

2020-10-05 · Benjin Zhu, Junqiang Huang, Zeming Li, Xiangyu Zhang 외

In this paper, we propose EqCo (Equivalent Rules for Contrastive Learning) to make self-supervised learning irrelevant to the number of negative samples in the contrastive learning framework. Inspired by the InfoMax prin…

Contrastive LearningLinear evaluationSelf-Supervised Learning

Residual Contrastive Learning: Unsupervised Representation Learning from Residuals

2021-09-29 · Nanqing Dong, Matteo Maggioni, Yongxin Yang, Eduardo Pérez-Pellitero 외

In the era of deep learning, supervised residual learning (ResL) has led to many breakthroughs in low-level vision such as image restoration and enhancement tasks. However, the question of how to formalize and take advan…

Contrastive LearningImage ReconstructionImage RestorationRepresentation Learning+1

Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space

2022-10-29 · Zhe Li, Man-Wai Mak, Helen Mei-Ling Meng

The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning. To overc…

Contrastive LearningSpeaker Verification