Related papers: Contrastive Semi-supervised Learning for ASR
Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training…
Self-Supervised Learning (SSL) enables us to pre-train foundation models without costly labeled data. Among SSL methods, Contrastive Learning (CL) methods are better at obtaining accurate semantic representations in noise interference.…
Semi-supervised learning (SSL) is a widely used technique in scenarios where labeled data is scarce and unlabeled data is abundant. While SSL is popular for image and text classification, it is relatively underexplored for the task of…
Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noisy label learning.…
Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To…
Federated semi-supervised learning (FSSL), facilitates labeled clients and unlabeled clients jointly training a global model without sharing private data. Existing FSSL methods predominantly employ pseudo-labeling and consistency…
Labels are costly and sometimes unreliable. Noisy label learning, semi-supervised learning, and contrastive learning are three different strategies for designing learning processes requiring less annotation cost. Semi-supervised learning…
To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…
Improving generalization is a major challenge in audio classification due to labeled data scarcity. Self-supervised learning (SSL) methods tackle this by leveraging unlabeled data to learn useful features for downstream classification…
In this paper, we apply Semi-Supervised Learning (SSL) along with Data Augmentation (DA) for improving the accuracy of End-to-End ASR. We focus on the consistency regularization principle, which has been successfully applied to image…
Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data is available for…
The lack of labeled data is a major obstacle in many music information retrieval tasks such as melody extraction, where labeling is extremely laborious or costly. Semi-supervised learning (SSL) provides a solution to alleviate the issue by…
Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of…
Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication. However, SER has long suffered from a lack of public large-scale labeled datasets. To circumvent this problem, we investigate how…
Pseudo-labeling is a commonly used paradigm in semi-supervised learning, yet its application to semi-supervised regression (SSR) remains relatively under-explored. Unlike classification, where pseudo-labels are discrete and confidence-based…
Sign language is the primary communication language for people with disabling hearing loss. Sign language recognition (SLR) systems aim to recognize sign gestures and translate them into spoken language. One of the main challenges in SLR is…
Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…
Semi-supervised object detection (SSOD) aims to boost detection performance by leveraging extra unlabeled data. The teacher-student framework has been shown to be promising for SSOD, in which a teacher network generates pseudo-labels for…
Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and…
Training deep models with limited annotations poses a significant challenge when applied to diverse practical domains. Employing semi-supervised learning alongside the self-supervised model offers the potential to enhance label efficiency.…