Related papers: Iterative Pseudo-Labeling for Speech Recognition

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…

Despite achieving impressive progress, current multi-label image recognition (MLR) algorithms heavily depend on large-scale datasets with complete labels, making collecting large-scale datasets extremely time-consuming and labor-intensive.…

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…

In the recent years, speech representation learning is constructed primarily as a self-supervised learning (SSL) task, using the raw audio signal alone, while ignoring the side-information that is often available for a given speech…

Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent…

Scribble-supervised medical image segmentation tackles the limitation of sparse masks. Conventional approaches alternate between: labeling pseudo-masks and optimizing network parameters. However, such iterative two-stage paradigm is…

Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are…

Active learning is a machine learning approach for reducing the data labeling effort. Given a pool of unlabeled samples, it tries to select the most useful ones to label so that a model built from them can achieve the best possible…

A significant issue in training deep neural networks to solve supervised learning tasks is the need for large numbers of labelled datapoints. The goal of semi-supervised learning is to leverage ubiquitous unlabelled data, together with…

When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect…

Many existing works on voice conversion (VC) tasks use automatic speech recognition (ASR) models for ensuring linguistic consistency between source and converted samples. However, for the low-data resource domains, training a high-quality…

While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL…

This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. The unlabeled images are usually assigned pseudo labels to be used…

Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical workaround, it often introduces systematic, accent-specific…

Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this…

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…

Non-intrusive intelligibility prediction is important for its application in realistic scenarios, where a clean reference signal is difficult to access. The construction of many non-intrusive predictors require either ground truth…

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional…

Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is important for self-supervised learning. We propose a simple…