Related papers: Audible Networks: Deconstructing and Manipulating …

Sound field decomposition predicts waveforms in arbitrary directions using signals from a limited number of microphones as inputs. Sound field decomposition is fundamental to downstream tasks, including source localization, source…

Hyperspectral imaging (HI) has emerged as a powerful tool in diverse fields such as medical diagnosis, industrial inspection, and agriculture, owing to its ability to detect subtle differences in physical properties through high spectral…

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are…

A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual…

Diffusion models have attained impressive visual quality for image synthesis. However, how to interpret and manipulate the latent space of diffusion models has not been extensively explored. Prior work diffusion autoencoders encode the…

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…

Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components.…

Neural fields excel in computer vision and robotics due to their ability to understand the 3D visual world such as inferring semantics, geometry, and dynamics. Given the capabilities of neural fields in densely representing a 3D scene from…

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Subsampling is used in convolutional neural networks (CNNs) in the form of pooling or strided convolutions, to reduce the spatial dimensions of feature maps and to allow the receptive fields to grow exponentially with depth. However, it is…

Low-dose computed tomography (LDCT) reduces the X-ray radiation but compromises image quality with more noises and artifacts. A plethora of transformer models have been developed recently to improve LDCT image quality. However, the success…

The efficacy of self-supervised speech models has been validated, yet the optimal utilization of their representations remains challenging across diverse tasks. In this study, we delve into Acoustic Word Embeddings (AWEs), a fixed-length…

We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed…

Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical…

Deep learning techniques have been used recently to tackle the audio source separation problem. In this work, we propose to use deep fully convolutional denoising autoencoders (CDAEs) for monaural audio source separation. We use as many…

Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…

Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are…

Audio segmentation is a key task for many speech technologies, most of which are based on neural networks, usually considered as black boxes, with high-level performances. However, in many domains, among which health or forensics, there is…

Denoising autoencoders (DAEs) are powerful deep learning models used for feature extraction, data generation and network pre-training. DAEs consist of an encoder and decoder which may be trained simultaneously to minimise a loss (function)…

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…