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.
We analyze a simple hierarchical architecture consisting of two multilayer perceptron (MLP) classifiers in tandem to estimate the phonetic class conditional probabilities. In this hierarchical setup, the first MLP classifier is trained using standard acous ...
In this thesis, we investigate a hierarchical approach for estimating the phonetic class-conditional probabilities using a multilayer perceptron (MLP) neural network. The architecture consists of two MLP classifiers in cascade. The first MLP is trained in ...
Using phone posterior probabilities has been increasingly explored for improving automatic speech recognition (ASR) systems. In this paper, we propose two approaches for hierarchically enhancing these phone posteriors, by integrating long acoustic context, ...
System identification using multiple-model strategies may involve thousands of models with several parameters. However, only a few models are close to the correct model. A key task involves finding which parameters are important for explaining candidate mo ...
Several object categorization algorithms use kernel methods over multiple cues, as they offer a principled ap- proach to combine multiple cues, and to obtain state-of-the- art performance. A general drawback of these strategies is the high computational co ...
We propose new soft-prior approach for incorporating structural a priori in FDOT reconstruction. The technique is a non-linear regularization scheme based on the penalization of the (2, 1)-mixed norm. We solve the numerical reconstruction problem with an i ...
Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2010
We propose new soft-prior approach for incorporating structural a priori in FDOT reconstruction. The technique is a non-linear regularization scheme based on the penalization of the (2, 1)-mixed norm. We solve the numerical reconstruction problem with an ...
Efficient learning from massive amounts of information is a hot topic in computer vision. Available training sets contain many examples with several visual descriptors, a setting in which current batch approaches are typically slow and does not scale well. ...
Efficient learning from massive amounts of information is a hot topic in computer vision. Available training sets contain many examples with several visual descriptors, a setting in which current batch approaches are typically slow and does not scale well. ...
Several object categorization algorithms use kernel methods over multiple cues, as they offer a principled ap- proach to combine multiple cues, and to obtain state-of-the- art performance. A general drawback of these strategies is the high computational co ...