Concept

Categorical distribution

Related publications (112)

Monte Carlo Video Text Segmentation

Jean-Philippe Thiran, Jean-Marc Odobez, Datong Chen

This paper presents a probabilistic algorithm for segmenting and recognizing text embedded in video sequences based on adaptive thresholding using a Bayes filtering method. The algorithm approximates the posterior distribution of segmentation thresholds of ...

2005

Kernelized Infomax Clustering

We propose a simple information-theoretic clustering approach based on maximizing the mutual information

I(\sfx,y)

between the unknown cluster labels

y

and the training patterns

\sfx

with respect to parameters of specifically constrained encoding dis ...

IDIAP2005

Phase AutoCorrelation (PAC) features in Entropy based Multi-Stream for Robust Speech Recognition

Hervé Bourlard, Hynek Hermansky, Hemant Misra, Shajith Ikbal

Methods to improve noise robustness of speech recognition systems often result in degradation of recognition performance for clean speech. Recently proposed Phase AutoCorrelation (PAC) \cite{ikbal03,ikbal03a} based features, showing noticeable improvement ...

2004

Posteriori Probabilities and Likelihoods Combination for Speech and Speaker Recognition

Hervé Bourlard

This paper investigates a new approach to perform simultaneous speech and speaker recognition. The likelihood estimated by a speaker identification system is combined with the posterior probability estimated by the speech recognizer. So, the joint posterio ...

IDIAP2004

Posteriori Probabilities and Likelihoods Combination for Speech and Speaker Recognition

Hervé Bourlard

2004

Phase AutoCorrelation (PAC) features in Entropy based Multi-Stream for Robust Speech Recognition

Hervé Bourlard, Hynek Hermansky, Hemant Misra, Shajith Ikbal

IDIAP2003

Confusion Matrix Based Entropy Correction in Multi-stream Combination

Hemant Misra

An MLP classifier outputs a posterior probability for each class. With noisy data, classification becomes less certain, and the entropy of the posteriors distribution tends to increase providing a measure of classification confidence. However, at high nois ...

2003

Polarizability and dielectric constant in density-functional supercell calculations with discrete k-point samplings

Alfredo Pasquarello

We address the dielectric constant (or the polarizability for an isolated system) as obtained in density-functional supercell calculations with a discrete k-point sampling. We compare a scheme based on conventional perturbational theory to one based on a d ...

2003

Confusion matrix based posterior probabilities correction

Hemant Misra

An MLP classifier outputs a posterior probability for each class. With noisy data classification becomes less certain and the entropy of the posteriors distribution tends to increase, therefore providing a measure of classification confidence. However, at ...

IDIAP2002

A Scalable Routing Method for Irregular Mobile Ad Hoc Networks

Jean-Yves Le Boudec, Ljubica Blazevic

We designed the terminode routing protoc ol with the objective to scale in large mobile ad hoc networks where the topology, or node distribution, is irregular. Our routing protocol is a combination of two protocols: Terminode Local Routing (TLR - to reach ...

2002

Graph Chatbot

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.