Related papers: Audiogmenter: a MATLAB Toolbox for Audio Data Augm…

In this paper we present ensembles of classifiers for automated animal audio classification, exploiting different data augmentation techniques for training Convolutional Neural Networks (CNNs). The specific animal audio classification…

End-to-end models have achieved significant improvement on automatic speech recognition. One common method to improve performance of these models is expanding the data-space through data augmentation. Meanwhile, human auditory inspired…

The classification of acoustic environments allows for machines to better understand the auditory world around them. The use of deep learning in order to teach machines to discriminate between different rooms is a new area of research.…

Data augmentation is a key tool for improving the performance of deep networks, particularly when there is limited labeled data. In some fields, such as computer vision, augmentation methods have been extensively studied; however, for…

Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained features like exact tempo or pitch, effective integration…

End-to-end Speech Translation is hindered by a lack of available data resources. While most of them are based on documents, a sentence-level version is available, which is however single and static, potentially impeding the usefulness of…

Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing…

End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-translation or…

Dementia is a growing problem as our society ages, and detection methods are often invasive and expensive. Recent deep-learning techniques can offer a faster diagnosis and have shown promising results. However, they require large amounts of…

The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…

Instrument classification is one of the fields in Music Information Retrieval (MIR) that has attracted a lot of research interest. However, the majority of that is dealing with monophonic music, while efforts on polyphonic material mainly…

In this paper, ensembles of classifiers that exploit several data augmentation techniques and four signal representations for training Convolutional Neural Networks (CNNs) for audio classification are presented and tested on three freely…

Data augmentation is a technique to generate new training data based on existing data. We evaluate the simple and cost-effective method of concatenating the original data examples to build new training instances. Continued training with…

The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learning and data augmentation to alleviate this issue. We study…

Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on. In this paper, we present NL-Augmenter, a new…

In this work, we propose a novel data augmentation method for clinical audio datasets based on a conditional Wasserstein Generative Adversarial Network with Gradient Penalty (cWGAN-GP), operating on log-mel spectrograms. To validate our…

Accurately interpreting cardiac auscultation signals plays a crucial role in diagnosing and managing cardiovascular diseases. However, the paucity of labelled data inhibits classification models' training. Researchers have turned to…

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…

Recent studies have identified that language models, pretrained on text-only datasets, often lack elementary visual knowledge, \textit{e.g.,} colors of everyday objects. Motivated by this observation, we ask whether a similar shortcoming…

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time…