Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling
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.
Code (1)
Tasks
Data AugmentationSelf-Supervised LearningSpeaker VerificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning
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 VerificationThe Phonexia VoxCeleb Speaker Recognition Challenge 2021 System Description
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 VerificationA Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding
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+8Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations
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 VerificationPushing the limits of self-supervised speaker verification using regularized distillation framework
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