Related papers: Self-Supervised Speaker Verification Using Dynamic…

Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances…

Very deep models for speaker recognition (SR) have demonstrated remarkable performance improvement in recent research. However, it is impractical to deploy these models for on-device applications with constrained computational resources. On…

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.…

In neural network based speaker verification, speaker embedding is expected to be discriminative between speakers while the intra-speaker distance should remain small. A variety of loss functions have been proposed to achieve this goal. In…

Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct…

Self-supervised learning (SSL) has transformed speech processing, with benchmarks such as SUPERB establishing fair comparisons across diverse downstream tasks. Despite it's security-critical importance, Audio deepfake detection has remained…

Deep representation learning has gained significant momentum in advancing text-dependent speaker verification (TD-SV) systems. When designing deep neural networks (DNN) for extracting bottleneck features, key considerations include training…

Recent semi-supervised learning methods use pseudo supervision as core idea, especially self-training methods that generate pseudo labels. However, pseudo labels are unreliable. Self-training methods usually rely on single model prediction…

Beyond attaining domain generalization (DG), visual recognition models should also be data-efficient during learning by leveraging limited labels. We study the problem of Semi-Supervised Domain Generalization (SSDG) which is crucial for…

In supervised speech separation, permutation invariant training (PIT) is widely used to handle label ambiguity by selecting the best permutation to update the model. Despite its success, previous studies showed that PIT is plagued by…

Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel…

Semi-supervised learning has received attention from researchers, as it allows one to exploit the structure of unlabeled data to achieve competitive classification results with much fewer labels than supervised approaches. The Local and…

The goal of this paper is to train effective self-supervised speaker representations without identity labels. We propose two curriculum learning strategies within a self-supervised learning framework. The first strategy aims to gradually…

Large performance degradation is often observed for speaker ver-ification systems when applied to a new domain dataset. Givenan unlabeled target-domain dataset, unsupervised domain adaptation(UDA) methods, which usually leverage adversarial…

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

Speaker diarization (SD) is typically used with an automatic speech recognition (ASR) system to ascribe speaker labels to recognized words. The conventional approach reconciles outputs from independently optimized ASR and SD systems, where…

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the…

Source-free domain adaptation (SFDA) utilizes a pre-trained source model with unlabeled target data. Self-supervised SFDA techniques generate pseudolabels from the pre-trained source model, but these pseudolabels often contain noise due to…