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.
This paper addresses the problem of representing multimedia information under a compressed form that permits efficient classification. The semantic coding problem starts from a subspace method where dimensionality reduction is formulated as a matrix factor ...
Visual behavior recognition is currently a highly active research area. This is due both to the scientific challenge posed by the complexity of the task, and to the growing interest in its applications, such as automated visual surveillance, human-computer ...
Phone posteriors has recently quite often used (as additional features or as local scores) to improve state-of-the-art automatic speech recognition (ASR) systems. Usually, better phone posterior estimates yield better ASR performance. In the present paper ...
We extend the standard boosting procedure to train a two-layer classifier dedicated to handwritten character recognition. The scheme we propose relies on a hidden layer which extracts feature vectors on a fixed number of points of interest, and an output l ...
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 ...
In this paper, we investigate the significance of contextual information in a phoneme recognition system using the hidden Markov model - artificial neural network paradigm. Contextual information is probed at the feature level as well as at the output of t ...
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 ...
Resources in the Grid exhibit different availability properties and patterns over time, mainly due to their administrators’ policies for the Grid, and the different domains to which they belong, e.g. non-dedicated desktop Grids, on-demand systems, P2P syst ...
This paper describes an approach where posterior-based features are applied in those recognition tasks where the amount of training data is insufficient to obtain a reliable estimate of the speech variability. A template matching approach is considered in ...
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 ...
