Related papers: On-the-fly Denoising for Data Augmentation in Natu…
Adversarial training has been shown effective at endowing the learned representations with stronger generalization ability. However, it typically requires expensive computation to determine the direction of the injected perturbations. In…
Deep neural networks (DNNs) often rely on massive labelled data for training, which is inaccessible in many applications. Data augmentation (DA) tackles data scarcity by creating new labelled data from available ones. Different DA methods…
To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…
In this paper, we perform an in-depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel variability, different audio compressions, different…
Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…
Despite remarkable progress on visual recognition tasks, deep neural-nets still struggle to generalize well when training data is scarce or highly imbalanced, rendering them extremely vulnerable to real-world examples. In this paper, we…
Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep models overfitting remains the largest problem, outweighing performance improvements…
Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, designing label-preserving transformations for text data tends…
Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…
Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing augmentation policies have so far been designed to only utilize labeled data, which limits the…
Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of…
In active learning, the focus is mainly on the selection strategy of unlabeled data for enhancing the generalization capability of the next learning cycle. For this, various uncertainty measurement methods have been proposed. On the other…
One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at…
Data cleansing is a well studied strategy for cleaning erroneous labels in datasets, which has not yet been widely adopted in Music Information Retrieval. Previously proposed data cleansing models do not consider structured (e.g. time…
Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…
Simple yet effective data augmentation techniques have been proposed for sentence-level and sentence-pair natural language processing tasks. Inspired by these efforts, we design and compare data augmentation for named entity recognition,…
Data augmentation has proven widely effective in computer vision. In Natural Language Processing (NLP) data augmentation remains an area of active research. There is no widely accepted augmentation technique that works well across tasks and…
Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation…
Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data. Such over-fitting ability hinders generalization when mislabeled training examples are present. On the other…
Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…