EMPIRICAL EVALUATION AND COMBINATION OF PUNCTUATION PREDICTION MODELS APPLIED TO BROADCAST NEWS
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.
Deep learning relies on a very specific kind of neural networks: those superposing several neural layers. In the last few years, deep learning achieved major breakthroughs in many tasks such as image analysis, speech recognition, natural language processin ...
This paper presents a general method for modeling extended-reaction surface impedance boundary conditions in time-domain wave-based room acoustic simulations. A sound field separation technique is used to separate the sound field at a boundary into its inc ...
The problem of adversarial robustness has been studied extensively for neural networks. However, for boosted decision trees and decision stumps there are almost no results, even though they are widely used in practice (e.g. XGBoost) due to their accuracy, ...
Detection of fidgeting activities is a field which has not been much explored as of now. Studies have shown that fidgeting has a beneficial impact on people’s healthiness as it burns a significant amount of energy. Being able to detect when someone is fidg ...
Uncertainty estimation in large deep-learning models is a computationally challenging task, where it is difficult to form even a Gaussian approximation to the posterior distribution. In such situations, existing methods usually resort to a diagonal approxi ...
In this paper, we propose a novel Deep Micro-Dictionary Learning and Coding Network (DDLCN). DDLCN has most of the standard deep learning layers (pooling, fully, connected, input/output, etc.) but the main difference is that the fundamental convolutional l ...
Recognition of objects with subtle differences has been used in many practical applications, such as car model recognition and maritime vessel identification. For discrimination of the objects in fine-grained detail, we focus on deep embedding learning by ...
Identifying nuclei is often a critical first step in analyzing microscopy images of cells and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluati ...
Natural language processing techniques are dependent upon punctuation to work well. When their input is taken from speech recognition, it is necessary to reconstruct the punctuation; in particular sentence boundaries. We define a range of features from low ...
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by an arbitrary grap ...
