Low-rank and Sparse Soft Targets to Learn Better DNN 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.

Speech recognition-based applications upon the advancements in artificial intelligence play an essential role to transform most aspects of modern life. However, speech recognition in real-life conditions (e.g., in the presence of overlapping speech, varyin ...

Atypical aspects in speech concern speech that deviates from what is commonly considered normal or healthy. In this thesis, we propose novel methods for detection and analysis of these aspects, e.g. to monitor the temporary state of a speaker, diseases tha ...

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

We present a statistical framework to benchmark the performance of reconstruction algorithms for linear inverse problems, in particular, neural-network-based methods that require large quantities of training data. We generate synthetic signals as realizati ...

A central question of machine learning is how deep nets manage to learn tasks in high dimensions. An appealing hypothesis is that they achieve this feat by building a representation of the data where information irrelevant to the task is lost. For image da ...

Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. Here we propose an ...

In recent years, there has been a significant revolution in the field of deep learning, which has demonstrated its effectiveness in automatically capturing intricate patterns from large datasets. However, the majority of these successes in Computer Vision ...

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 ...

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits. In th ...

This study presents a self-supervised Bayesian Neural Network (BNN) framework using air-borne Acoustic Emission (AE) to identify different Laser Powder Bed Fusion (LPBF) process regimes such as Lack of Fusion, conduction mode, and keyhole without ground-tr ...

The development of low-power wearable systems requires specialized techniques to accommodate their unique requirements and constraints. While significant advancements have been made in the inference phase of artificial intelligence, the training phase rema ...

Deep neural networks (DNN) have become an essential tool to tackle challenging tasks in many fields of computer science. However, their high computational complexity limits their applicability. Specialized DNN accelerators have been developed to accommodat ...

In recent years, new emerging immersive imaging modalities, e.g. light fields, have been receiving growing attention, becoming increasingly widespread over the years. Light fields are often captured through multi-camera arrays or plenoptic cameras, with th ...

Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models

Chat with Graph Search

Sparse Autoencoders for Speech Modeling and Recognition

Novel Methods For Detection And Analysis Of Atypical Aspects In Speech

Supervised learning and inference of spiking neural networks with temporal coding

A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods

How deep convolutional neural networks lose spatial information with training

An exact mapping from ReLU networks to spiking neural networks

Deep Learning for 3D Surface Modelling and Reconstruction

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

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Self-Supervised Bayesian representation learning of acoustic emissions from laser powder bed Fusion process for in-situ monitoring

Layer-Wise Learning Framework for Efficient DNN Deployment in Biomedical Wearable Systems

Hardware-Software Co-design for Improved Resource Utilization in DNN Accelerators

Towards learning-based denoising of light fields