Publications related to What is Better: GMM of Two Gaussians or Two Clusters With One Gaussian?

Optimal lower bounds on hitting probabilities for non-linear systems of stochastic fractional heat equations

We consider a system of d non-linear stochastic fractional heat equations in spatial dimension 1 driven by multiplicative d-dimensional space-time white noise. We establish a sharp Gaussian-type upper bound on the two-point probability density function of ...

ELSEVIER2021

A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers

Philip Neil Garner

Neural Network (NN) classifiers can assign extreme probabilities to samples that have not appeared during training (out-of-distribution samples) resulting in erroneous and unreliable predictions. One of the causes for this unwanted behaviour lies in the us ...

IEEE2020

A Bayesian Approach To Inter-Task Fusion For Speaker Recognition

Petr Motlicek, Subhadeep Dey

In i-vector based speaker recognition systems, back-end classifiers are trained to factor out nuisance information and retain only the speaker identity. As a result, variabilities arising due to gender, language and accent ( among many others) are suppress ...

IEEE2019

A BAYESIAN APPROACH TO INTER-TASK FUSION FOR SPEAKER RECOGNITION

Petr Motlicek, Subhadeep Dey

In i-vector based speaker recognition systems, back-end classifiers are trained to factor out nuisance information and retain only the speaker identity. As a result, variabilities arising due to gender, language and accent ( among many others) are suppress ...

2019

Gaussian Process Regression for Maximum Entropy Distribution

Mohsen Sadr

Maximum-Entropy Distributions offer an attractive family of probability densities suitable for moment closure problems. Yet finding the Lagrange multipliers which parametrize these distributions, turns out to be a computational bottleneck for practical clo ...

2019

The stochastic heat equation: hitting probabilities and the probability density function of the supremum via Malliavin calculus

Fei Pu

In this thesis, we study systems of linear and/or non-linear stochastic heat equations and fractional heat equations in spatial dimension

1

driven by space-time white noise. The main topic is the study of hitting probabilities for the solutions to these ...

EPFL2018

Comparing methodologies for structural identification and fatigue life prediction of a highway bridge

Ian Smith, Alain Nussbaumer, Sai Ganesh Sarvotham Pai

Accurate measurement-data interpretation leads to increased understanding of structural behavior and enhanced asset-management decision making. In this paper, four data-interpretation methodologies, residual minimization, traditional Bayesian model updatin ...

2018

Performance monitoring for brain-computer-interface actions

Olaf Blanke, Aaron Schurger, Steven Gale, Olivia Gozel

When presented with a difficult perceptual decision, human observers are able to make metacognitive judgements of subjective certainty. Such judgements can be made independently of and prior to any overt response to a sensory stimulus, presumably via inter ...

Elsevier2017

Systems and methods for tracking interacting objects

Pascal Fua, François Fleuret, Engin Türetken, Xinchao Wang

Systems and methods for tracking interacting objects may acquire, with a sensor, and two or more images associated with two or more time instances. A processor may generate image data from the two or more images. The processor may apply an extended Probabi ...

2015

Overlapping speech detection using long-term conversational features for speaker diarization in meeting room conversations

Hervé Bourlard, Sree Harsha Yella

Overlapping speech has been identified as one of the main sources of errors in diarization of meeting room conversations. Therefore, overlap detection has become an important step prior to speaker diarization. Studies on conversational analysis have shown ...

2014

What is Better: GMM of Two Gaussians or Two Clusters With One Gaussian?

Graph Chatbot

Chat with Graph Search

Optimal lower bounds on hitting probabilities for non-linear systems of stochastic fractional heat equations

A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers

A Bayesian Approach To Inter-Task Fusion For Speaker Recognition

A BAYESIAN APPROACH TO INTER-TASK FUSION FOR SPEAKER RECOGNITION

Gaussian Process Regression for Maximum Entropy Distribution

The stochastic heat equation: hitting probabilities and the probability density function of the supremum via Malliavin calculus

Comparing methodologies for structural identification and fatigue life prediction of a highway bridge

Performance monitoring for brain-computer-interface actions

Systems and methods for tracking interacting objects

Overlapping speech detection using long-term conversational features for speaker diarization in meeting room conversations

Optimal lower bounds on hitting probabilities for non-linear systems of stochastic fractional heat equations

A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers

The stochastic heat equation: hitting probabilities and the probability density function of the supremum via Malliavin calculus

A BAYESIAN APPROACH TO INTER-TASK FUSION FOR SPEAKER RECOGNITION

Gaussian Process Regression for Maximum Entropy Distribution

Performance monitoring for brain-computer-interface actions

A Bayesian Approach To Inter-Task Fusion For Speaker Recognition

Comparing methodologies for structural identification and fatigue life prediction of a highway bridge

Systems and methods for tracking interacting objects

Overlapping speech detection using long-term conversational features for speaker diarization in meeting room conversations