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.
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 ...
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 ...
Bayesian inference of posterior parameter distributions has become widely used in hydrological modeling to estimate the associated modeling uncertainty. The classical underlying statistical model assumes a Gaussian modeling error with zero mean and a given ...
In this paper, we present initial results towards boosting posterior based speech recognition systems by estimating more informative posteriors using multiple streams of features and taking into account acoustic context (e.g., as available in the whole utt ...
In this paper, we present initial results towards boosting posterior based speech recognition systems by estimating more informative posteriors using multiple streams of features and taking into account acoustic context (e.g., as available in the whole utt ...
e consider an estimation network of many distributed sensors, where each senor takes a noisy measurement of some unknown parameter. Due to energy limitation, the network selects only a subset of sensors for data fusion as long as the distortion is tolerabl ...
This work describes a solution to the validation challenge problem posed at the SANDIA Validation Challenge Workshop, May 21-23, 2006, NM. It presents and applies a general methodology to it. The solution entails several standard steps, namely selecting an ...
Glycine is an amino acid present in mammalian brain, where it acts as an inhibitory and excitatory neurotransmitter. The two detectable protons of glycine give rise to a singlet at 3.55 ppm that overlaps with the more intense myo-inositol resonances, and i ...
In this paper we deal with the multi-object tracking problem in the particular case of pedestrians, assuming the detection step already done. We use a Bayesian framework to combine the likelihood term provided by an image correlation algorithm with a prior ...
We present an approach to create hyper-links between video segments that contain objects of interest, based on video structuring, object definition, and stochastic object localization in the video structure. Localization is formulated in the Metric Mixture ...