Blind Audiovisual Source Separation Using Sparse Representations

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Humans and animals both use acoustic signals for vocal communication. The advent of self-supervised learning (SSL) has enabled neural networks to learn robust and general feature representations through the intrinsic acoustic structure of input signals, wi ...

Neural decoding of the visual system is a subject of research interest, both to understand how the visual system works and to be able to use this knowledge in areas, such as computer vision or brain-computer interfaces. Spike-based decoding is often used, ...

In the last few years, stroke ranked as the second most common cause of death and is the third most significant condition affecting disability-adjusted life years (DALYs) worldwide. Being the most prevalent and quality of life impacting post-stroke symptom ...

Efficient information retrieval is a fundamental requirement in a wide array of applications, ranging from bioinformatics to database systems, and critically hinges on the complexity of an underlying distance metric. This work presents a novel approach to ...

Electrical stimulation of the visual nervous system could improve the quality of life of patients affected by acquired blindness by restoring some visual sensations, but requires careful optimization of stimulation parameters to produce useful perceptions. ...

Viewers of 360-degree videos are provided with both visual modality to characterize their surrounding views and audio modality to indicate the sound direction. Though both modalities are important for saliency prediction, little work has been done by joint ...

Reciprocity guarantees that in most media, sound transmission is symmetric between two points of space when the location of the source and receiver are interchanged. This fundamental law can be broken in non-linear media, often at the cost of detrimental i ...

Objective. Artificial vision has been and still is the subject of intense research. The ultimate goal is to help blind people in their daily life. Approaches to artificial vision, including visual prostheses and optogenetics, have strongly focused on resto ...

We discuss the effects of image scanning microscopy using doughnut beam illumination on the properties of signal strength and integrated intensity. Doughnut beam illumination can give better optical sectioning and background rejection than Airy disk illumi ...

Systematic compositionality, or the ability to adapt to novel situations by creating a mental model of the world using reusable pieces of knowledge, remains a significant challenge in machine learning. While there has been considerable progress in the lang ...

BackgroundInterstitial lung diseases (ILD), such as idiopathic pulmonary fibrosis (IPF) and non-specific interstitial pneumonia (NSIP), and chronic obstructive pulmonary disease (COPD) are severe, progressive pulmonary disorders with a poor prognosis. Prom ...

Knowing where objects are relative to us implies knowing where we are relative to the external world. Here, we investigated whether space perception can be influenced by an experimentally induced change in perceived self-location. To dissociate real and ap ...

Technological progress in materials science and microengineering along with new discoveries in neuroscience have contributed to restore lost or impaired sensory functions by closely interfacing with the nervous system. Electronic devices have begun to be i ...

Voice activity detection (VAD) is an important pre-processing step for speech technology applications. The task consists of deriving segment boundaries of audio signals which contain voicing information. In recent years, it has been shown that voice source ...

Understanding the influence of running-induced acute fatigue on the homeostasis of the body is essential to mitigate the adverse effects and optimize positive adaptations to training. Fatigue is a multifactorial phenomenon, which influences biomechanical, ...

A remote microphone (RM) system can be used in combination with wearable binaural communication devices, such as hearing aids (HAs), to improve speech intelligibility. Typically, a speaker is equipped with a body-worn microphone which enables to pick up th ...

Introduction Recent work has shown an association between cognitive and visual impairments and two main theories were advanced, namely the sensory deprivation and the common cause theories. Most studies considered only basic visual functions such as visual ...

A method for operating a light microscope comprises emitting and guiding a plurality of illumination light beams towards a specimen (6) to form a plurality of separated illumination light spots (2A, 2B, 2C, 2D) at the specimen; and guiding detection light ...

Community structure in graph-modeled data appears in a range of disciplines that comprise network science. Its importance relies on the influence it bears on other properties of graphs such as resilience, or prediction of missing connections. Nevertheless, ...

In this thesis, timing is everything. In the first part, we mean this literally, as we tackle systems that encode information using timing alone. In the second part, we adopt the standard, metaphoric interpretation of this saying and show the importance of ...

Blind Audiovisual Source Separation Using Sparse Representations

Chat with Graph Search

Transferability of Learnt Speech Representations for Decoding Non-Human Vocal Communication

Predicting Visual Stimuli From Cortical Response Recorded With Wide-Field Imaging in a Mouse

Probing and modulating inter-areal coupling in the cortical visual motion processing pathway with non-invasive brain stimulation

Efficient Neural Clustering and Compression of Strings Through Approximate Euclidean Embeddings of the Levenshtein Distance

Decoding electroencephalographic responses to visual stimuli compatible with electrical stimulation

SVGC-AVA: 360-Degree Video Saliency Prediction With Spherical Vector-Based Graph Convolution and Audio-Visual Attention

Observation of non-reciprocal harmonic conversion in real sounds

The role of the visual field size in artificial vision

Image scanning microscopy with a doughnut beam: signal strength and integrated intensity

Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models

Deep learning diagnostic and severity-stratification for interstitial lung diseases and chronic obstructive pulmonary disease in digital lung auscultations and ultrasonography: clinical protocol for an observational case-control study

The full-body illusion changes visual depth perception

Fabrication and validation of an intraneural interface tailored for optic nerve stimulation

Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering

Concurrent Evolution of Biomechanical and Physiological Parameters With Running-Induced Acute Fatigue

Auditory externalization of a remote microphone signal

No Common Factor Underlying Decline of Visual Abilities in Mild Cognitive Impairment

Method and light microscope with a plurality of arrays of photon-counting detector elements

Graph signal processing tailored for subgraph focus and community structure

Timing is Everything