Disentangling feature and lazy training in deep neural networks
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.
In this paper we propose a new technique for robust keyword spotting that uses bidirectional Long Short-Term Memory (BLSTM) recurrent neural nets to incorporate contextual information in speech decoding. Our approach overcomes the drawbacks of generative H ...
This paper investigates the use of a hierarchy of Neural Networks for performing data driven feature extraction. Two different hierarchical structures based on long and short temporal context are considered. Features are tested on two different LVCSR syste ...
We investigate a multilayer perceptron (MLP) based hierarchical approach for task adaptation in automatic speech recognition. The system consists of two MLP classifiers in tandem. A well-trained MLP available off-the-shelf is used at the first stage of the ...
The raindrop size distribution (RSD) is a critical factor in estimating rain intensity using advanced dual-polarized weather radars. A new neural-network algorithm to estimate the RSD from S-band dual-polarized radar measurements is presented. The correspo ...
In a recent paper, we reported promising automatic speech recognition results obtained by appending spectral entropy features to PLP features. In the present paper, spectral entropy features are used along with PLP features in the framework of multi-stream ...
In this paper, using the mathematical properties of self-kronecker-production of small size random matrices, a simple but effective method is presented to optimize the reservoir of an echo state network given a certain task. The experimental results invest ...
This paper investigates the use of a hierarchy of Neural Networks for performing data driven feature extraction. Two different hierarchical structures based on long and short temporal context are considered. Features are tested on two different LVCSR syste ...
In spite of more than 100 years of research, the mechanisms underlying visual masking are still unknown. In recent publications, we introduced an unmasking paradigm involving the fusion of features that revealed interesting spatial characteristics. Here, w ...
We present a data-driven approach to weighting the temporal context of signal energy to be used in a simple speech/non-speech detector (SND). The optimal weights are obtained using linear discriminant analysis (LDA). Regularization is performed to handle n ...
We present a biologically-inspired neural model addressing the problem of transformations across frames of reference in a posture imitation task. Our modeling is based on the hypothesis that imitation is mediated by two concurrent transformations selective ...
