Related papers: Leveraging Pre-Trained Autoencoders for Interpreta…

Human infant learning happens during exploration of the environment, by interaction with objects, and by listening to and repeating utterances casually, which is analogous to unsupervised learning. Only occasionally, a learning infant would…

In the context of environmental sound classification, the adaptability of systems is key: which sound classes are interesting depends on the context and the user's needs. Recent advances in text-to-audio retrieval allow for zero-shot audio…

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such…

This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike conventional Transducers where the decoder embeddings for different tokens are trained independently, the PET model's decoder embedding incorporates shared…

Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenarios due to the fact that deep transformers are hard to train…

In this work, we provide a broad comparative analysis of strategies for pre-training audio understanding models for several tasks in the music domain, including labelling of genre, era, origin, mood, instrumentation, key, pitch, vocal…

Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pretraining architectures and objectives within the masked autoencoding…

In this paper, we present a joint compression and classification approach of EEG and EMG signals using a deep learning approach. Specifically, we build our system based on the deep autoencoder architecture which is designed not only to…

Acoustic Event Classification (AEC) has become a significant task for machines to perceive the surrounding auditory scene. However, extracting effective representations that capture the underlying characteristics of the acoustic events is…

An autoencoder (AE) is a neural network that, using self-supervised training, learns a succinct parameterized representation, and a corresponding encoding and decoding process, for all instances in a given class. Here, we introduce the…

Transformers have been widely applied in text classification. Unfortunately, real-world data contain anomalies and noisy labels that cause challenges for state-of-art Transformers. This paper proposes Protoformer, a novel self-learning…

We study the usability of pre-trained weakly supervised audio tagging (AT) models as feature extractors for general audio representations. We mainly analyze the feasibility of transferring those embeddings to other tasks within the speech…

We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical…

Recent applications of deep convolutional neural networks in medical imaging raise concerns about their interpretability. While most explainable deep learning applications use post hoc methods (such as GradCAM) to generate feature…

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…

Categories can be represented at different levels of abstraction, from prototypes focused on the most typical members to remembering all observed exemplars of the category. These representations have been explored in the context of…

Multi-label classification is the challenging task of predicting the presence and absence of multiple targets, involving representation learning and label correlation modeling. We propose a novel framework for multi-label classification,…

Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model…

Federated learning is a specific distributed learning paradigm in which a central server aggregates updates from multiple clients' local models, thereby enabling the server to learn without requiring clients to upload their private data,…

This paper has proposed a new baseline deep learning model of more benefits for image classification. Different from the convolutional neural network(CNN) practice where filters are trained by back propagation to represent different…