paper-with-me

홈 › Papers

Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling

2025-01-29 · Theo Lepage, Reda Dehak

Recent developments in Self-Supervised Learning (SSL) have demonstrated significant potential for Speaker Verification (SV), but closing the performance gap with supervised systems remains an ongoing challenge. Standard SSL frameworks rely on anchor-positive pairs extracted from the same audio utterances. Hence, positives have channel characteristics similar to those of their corresponding anchors, even with extensive data-augmentation. Therefore, this positive sampling strategy is a fundamental limitation as it encodes too much information regarding the recording source in the learned representations. This article introduces Self-Supervised Positive Sampling (SSPS), a bootstrapped technique for sampling appropriate and diverse positives in SSL frameworks for SV. SSPS samples positives close to their anchor in the representation space, under the assumption that these pseudo-positives belong to the same speaker identity but correspond to different recording conditions. This method demonstrates consistent improvements in SV performance on VoxCeleb benchmarks when implemented in major SSL frameworks, such as SimCLR, SwAV, VICReg, and DINO. Using SSPS, SimCLR, and DINO achieve 2.57% and 2.53% EER on VoxCeleb1-O. SimCLR yields a 58% relative reduction in EER, getting comparable performance to DINO with a simpler training framework. Furthermore, SSPS lowers intra-class variance and reduces channel information in speaker representations while exhibiting greater robustness without data-augmentation.

📄 PDF Abstract BibTeX arXiv:2501.17772

Code (1)

theolepage/sslsv 공식 구현 pytorch

Tasks

Data AugmentationSelf-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
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
NT-Xent NT-Xent, or Normalized Temperature-scaled Cross Entropy Loss, is a loss function. Let $\text{sim}\left(\mathbf{u}, \mathbf{v}\right) =…
Multi-Head Attention 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning

2022-07-12 · Théo Lepage, Réda Dehak

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 …

Contrastive LearningData AugmentationSelf-Supervised LearningSpeaker Verification

The Phonexia VoxCeleb Speaker Recognition Challenge 2021 System Description

2021-09-05 · Josef Slavíček, Albert Swart, Michal Klčo, Niko Brümmer

We describe the Phonexia submission for the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21) in the unsupervised speaker verification track. Our solution was very similar to IDLab's winning submission for VoxSRC-2…

ClusteringContrastive LearningSpeaker RecognitionSpeaker Verification

A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding

2021-11-04 · Yingzhi Wang, Abdelmoumene Boumadane, Abdelwahab Heba

Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary progress in Automatic Speech Recognition (ASR). However, they have not been totally proven to produce better performance on tasks othe…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Emotion Recognitionintent-classification+8

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-bas…

Self-Supervised LearningSpeaker Verification

Pushing the limits of self-supervised speaker verification using regularized distillation framework

2022-11-08 · Yafeng Chen, Siqi Zheng, Hui Wang, Luyao Cheng 외

Training robust speaker verification systems without speaker labels has long been a challenging task. Previous studies observed a large performance gap between self-supervised and fully supervised methods. In this paper,…

Data AugmentationDiversitySelf-Supervised LearningSpeaker Verification