Related papers: Improved Techniques for the Conditional Generative…

The use of deep learning for radio modulation recognition has become prevalent in recent years. This approach automatically extracts high-dimensional features from large datasets, facilitating the accurate classification of modulation…

Small datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases…

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or…

Automated detection and classification of marine mammals vocalizations is critical for conservation and management efforts but is hindered by limited annotated datasets and the acoustic complexity of real-world marine environments. Data…

Data augmentation plays a key role in modern machine learning pipelines. While numerous augmentation strategies have been studied in the context of computer vision and natural language processing, less is known for other data modalities.…

Performance of sound event localization and detection (SELD) in real scenes is limited by small size of SELD dataset, due to difficulty in obtaining sufficient amount of realistic multi-channel audio data recordings with accurate label. We…

A mixed sample data augmentation strategy is proposed to enhance the performance of models on audio scene classification, sound event classification, and speech enhancement tasks. While there have been several augmentation methods shown to…

Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of…

Deep learning approaches to breast cancer detection in mammograms have recently shown promising results. However, such models are constrained by the limited size of publicly available mammography datasets, in large part due to privacy…

Acoustic environments affect acoustic characteristics of sound to be recognized by physically interacting with sound wave propagation. Thus, training acoustic models for audio and speech tasks requires regularization on various acoustic…

Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data…

In the ever-evolving landscape of social network advertising, the volume and accuracy of data play a critical role in the performance of predictive models. However, the development of robust predictive algorithms is often hampered by the…

In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training examples. While these…

Generative adversarial networks (GANs) have shown potential in learning emotional attributes and generating new data samples. However, their performance is usually hindered by the unavailability of larger speech emotion recognition (SER)…

This paper investigates methods for improving generative data augmentation for deep learning. Generative data augmentation leverages the synthetic samples produced by generative models as an additional dataset for classification with small…

Data augmentation has become a crucial component to train state-of-the-art visual representation models. However, handcrafting combinations of transformations that lead to improved performances is a laborious task, which can result in…

Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored…

Supervised training of an automated medical image analysis system often requires a large amount of expert annotations that are hard to collect. Moreover, the proportions of data available across different classes may be highly imbalanced…

Data augmentation is essential when applying Machine Learning in small-data regimes. It generates new samples following the observed data distribution while increasing their diversity and variability to help researchers and practitioners…

In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network engineering and classification tasks. The idea here is to…