Concept

Divergence de Bregman

Publications associées (62)

A novel framework for noise robust ASR using cochlear implant-like spectrally reduced speech

We propose a novel framework for noise robust automatic speech recognition (ASR) based on cochlear implant-like spectrally reduced speech (SRS). Two experimental protocols (EPs) are proposed in order to clarify the advantage of using SRS for noise robust A ...

2011

Kullback–Leibler Divergence as a Forecast Skill Score with Classic Reliability–Resolution–Uncertainty Decomposition

Steven Vincent Weijs, Nicolaas Cornelis van de Giesen

This paper presents a score that can be used for evaluating probabilistic forecasts of multicategory events. The score is a reinterpretation of the logarithmic score or ignorance score, now formulated as the relative entropy or Kullback–Leibler divergence ...

2010

Modelling Complex Fenestration Systems using physical and virtual models

Jean-Louis Scartezzini, Anothai Thanachareonkit

Physical or virtual models are commonly used to visualize the conceptual ideas of architects, lighting designers and researchers; they are also employed to assess the daylighting performance of buildings, particularly in cases where Complex Fenestration Sy ...

2010

NMR and NQR study of the tetrahedral frustrated quantum spin system Cu2Te2O5Br2 in its paramagnetic phase

Arnaud Comment

The quantum antiferromagnet Cu2Te2O5Br2 was investigated by NMR and nuclear quadrupole resonance (NQR). The Te-125 NMR investigation showed that there is a magnetic transition around 10.5 K at 9 T, in agreement with previous studies. From the divergence of ...

2010

Minimizing lighting power density in office rooms equipped with Anidolic Daylighting Systems

Jean-Louis Scartezzini, Friedrich Linhart

2010

Using KL-based Acoustic Models in a Large Vocabulary Recognition Task

Hervé Bourlard, Guillermo Aradilla

Posterior probabilities of sub-word units have been shown to be an effective front-end for ASR. However, attempts to model this type of features either do not benefit from modeling context-dependent phonemes, or use an inefficient distribution to estimate ...

IDIAP2008

Using Comparison of Parallel Phoneme Probability streams for OOV Word Detection

Mathew Magimai Doss, Hynek Hermansky, Tamara Tosic

In this paper, we investigate the approach of comparing two different parallel streams of phoneme posterior probability estimates for OOV word detection. The ﬁrst phoneme posterior probability stream is estimated using only the knowledge of short-term acou ...

2008

Acoustic models for posterior features in speech recognition

Guillermo Aradilla

In this thesis, we investigate the use of posterior probabilities of sub-word units directly as input features for automatic speech recognition (ASR). These posteriors, estimated from data-driven methods, display some favourable properties such as increase ...

EPFL2008

Acoustic Models for Posterior Features in Speech Recognition

Guillermo Aradilla

Ecole Polytechnique Fédérale de Lausanne2008

Acoustic Models for Posterior Features in Speech Recognition

Guillermo Aradilla

Idiap2008

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search