Lattice-Free Mmi Adaptation Of Self-Supervised Pretrained Acoustic Models

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.

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Mitigating the energy requirements of artificial intelligence requires novel physical substrates for computation. Phononic metamaterials have vanishingly low power dissipation and hence are a prime candidate for green, always-on computers. However, their u ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Despite the importance and pervasiveness of Wikipedia as one of the largest platforms for open knowledge, surprisingly little is known about how people navigate its content when seeking information. To bridge this gap, we present the first systematic large ...

Self-supervised learning (SSL) models use only the intrinsic structure of a given signal, independent of its acoustic domain, to extract essential information from the input to an embedding space. This implies that the utility of such representations is no ...

Background and Objective: Event-based analog-to-digital converters allow for sparse bio-signal acquisition, enabling local sub-Nyquist sampling frequency. However, aggressive event selection can cause the loss of important bio-markers, not recoverable with ...

Chronic pain presents a tremendous personal, societal, and financial burden. Treatment options are often limited to managing symptoms as opposed to treating the causes, and the consequences of pharmacological treatments can be immensely harmful as evidence ...

This paper presents a distributed shadow dynamic consensus (DSDC) framework to address the generation company (GENCO) strategic bidding problem in the independent system operator (ISO) operation. First, each sub-group is defined according to the communicat ...

Background and Objective: Cough audio signal classification is a potentially useful tool in screening for respiratory disorders, such as COVID-19. Since it is dangerous to collect data from patients with contagious diseases, many research teams have turned ...

Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...

This paper proposes high-order accurate well-balanced (WB) energy stable (ES) adaptive moving mesh finite difference schemes for the shallow water equations (SWEs) with non flat bottom topography. To enable the construction of the ES schemes on moving mesh ...

Computational models have been widely employed to study the electrical stimulation of the nervous system. Still, most applications either study fundamental mechanisms underlying stimulation, or address qualitative scientific questions. When quantitative qu ...

Lattice-Free Mmi Adaptation Of Self-Supervised Pretrained Acoustic Models

Chat with Graph Search

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

The multimodality cell segmentation challenge: toward universal solutions

Robust machine learning for neuroscientific inference

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

In-Sensor Passive Speech Classification with Phononic Metamaterials

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Meta-learning to address diverse Earth observation problems across resolutions

Aggregating Spatial and Photometric Context for Photometric Stereo

Topics in statistical physics of high-dimensional machine learning

Random matrix methods for high-dimensional machine learning models

A Large-Scale Characterization of How Readers Browse Wikipedia

Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?

Event-based sampled ECG morphology reconstruction through self-similarity

A Stand-Alone Augmented Reality Intervention for Chronic Pain using Embodied Systolic Stimulation

Distributed Shadow Dynamic Consensus Optimization Framework for Power Market with Parameterization Bidding Strategy of GENCOs

A semi-supervised algorithm for improving the consistency of crowdsourced datasets: The COVID-19 case study on respiratory disorder classification

Text Representation Learning for Low Cost Natural Language Understanding

High-order accurate well-balanced energy stable adaptive moving mesh finite difference schemes for the shallow water equations with non-flat bottom topography

Machine-learning predictor of nerve fiber firing rate allows the automatic optimization of electrical stimulation protocols