Open-Vocabulary Keyword Spotting with Audio and Text Embeddings

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.

Motivation Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretati ...

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

The current machine learning paradigm relies on continuous representations and fixed neural network architectures to approximate environmental structures, leading to challenges with continual learning, internal structure design, and goal-directed behavior ...

Understanding the structure of real data is paramount in advancing modern deep-learning methodologies. Natural data such as images are believed to be composed of features organized in a hierarchical and combinatorial manner, which neural networks capture d ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

Metal plasticity is an inherently multiscale phenomenon due to the complex long-range field of atomistic dislocations that are the primary mechanism for plastic deformation in metals. Atomistic/Continuum (A/C) coupling methods are computationally efficient ...

This paper proposes a novel approach to improve the performance of distributed nonlinear control systems while preserving stability by leveraging Deep Neural Networks (DNNs). We build upon the Neural System Level Synthesis (Neur-SLS) framework and introduc ...

Raw data associated to the manuscript ‘’Spin wave dispersion of ultra-low damping hematite (α-Fe2O3) at GHz frequencies‘’, Physical Review Materials 7, 054407(2023); doi: 10.1103/PhysRevMaterials.7.054407 Information about file fo ...

Over the past years, image generation and manipulation have achieved remarkable progress due to the rapid development of generative AI based on deep learning. Recent studies have devoted significant efforts to address the problem of face image manipulation ...

Reducing the computational time required by high-fidelity, full-order models (FOMs) for the solution of problems in cardiac mechanics is crucial to allow the translation of patient-specific simulations into clinical practice. Indeed, while FOMs, such as th ...

A new and efficient magnetisation transfer P-31 magnetic resonance fingerprinting (MT-P-31-MRF) approach is introduced to measure the creatine kinase metabolic rate kCK

{k}_{\mathrm{CK}}

between phosphocreatine (PCr) and adenosine triphosphate (ATP) i ...

We perform an error analysis of a fully discretised Streamline Upwind Petrov Galerkin Dynamical Low Rank (SUPG-DLR) method for random time-dependent advection-dominated problems. The time integration scheme has a splitting-like nature, allowing for potenti ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

In this paper we will consider distributed Linear-Quadratic Optimal Control Problems dealing with Advection-Diffusion PDEs for high values of the Peclet number. In this situation, computational instabilities occur, both for steady and unsteady cases. A Str ...

We propose an image-based elastography method to measure the heterogeneous stiffness inside a cell and its nucleus. It uses a widely accessible setup consisting of plate compression imaged with fluorescence microscopy. Our framework recovers a spatial map ...

Electrochemical sensors play a pivotal role in advancing therapeutic drug monitoring (TDM) and personalized therapy. However, the insufficient selectivity of electrochemical sensors based on cytochromes P450 poses a great need for innovative machine learni ...

In this work, we develop a new framework for dynamic network flow pro-blems based on optimal transport theory. We show that the dynamic multicommodity minimum-cost network flow problem can be formulated as a multimarginal optimal transport problem, where t ...

The rapid development of wearable biomedical systems now enables real-time monitoring of electroencephalography (EEG) signals. Acquisition of these signals relies on electrodes. These systems must meet the design challenge of selecting an optimal set of el ...

Open-Vocabulary Keyword Spotting with Audio and Text Embeddings

Chat with Graph Search

A comparative analysis of gene expression profiling by statistical and machine learning approaches

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Modelleyen: Continual Learning and Planning via Structured Modelling of Environment Dynamics

A phase transition in diffusion models reveals the hierarchical nature of data

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Learning to Reason with Neural Networks: Principles and Methods

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Lattice Green's function method for Atomistic/Continuum coupling

Optimal distributed control with stability guarantees by training a network of neural closed-loop maps

Spin wave dispersion of ultra-low damping hematite (α-Fe2O3) at GHz frequencies

Towards the Detection of AI-Synthesized Human Face Images

Efficient approximation of cardiac mechanics through reduced-order modeling with deep learning-based operator approximation

Fast in vivo assay of creatine kinase activity in the human brain by P-31 magnetic resonance fingerprinting

Error estimates for SUPG-stabilised Dynamical Low Rank Approximations

Understanding generalization and robustness in modern deep learning

A Streamline Upwind Petrov-Galerkin Reduced Order Method for Advection-Dominated Partial Differential Equations Under Optimal Control

PROBING INTRACELLULAR ELASTICITY WITH MINIMAL-HESSIAN REGISTRATION

Identification and Quantification of Multiple Drugs by Machine Learning on Electrochemical Sensors for Therapeutic Drug Monitoring

Scalable Computation of Dynamic Flow Problems via Multimarginal Graph-Structured Optimal Transport

FETCH: A Fast and Efficient Technique for Channel Selection in EEG Wearable Systems