In this paper, we propose a robust compensation strategy to deal effectively with extraneous acoustic variations for spontaneous speech recognition. This strategy extends speaker a...
This paper introduces a strategy for training ensemble classifiers by analysing boosting within margin theory. We present a bound on the generalisation error of ensembled classifi...
Huma Lodhi, Grigoris J. Karakoulas, John Shawe-Tay...
The Noise Sensitivity Signature (NSS), originally introduced by Grossman and Lapedes (1993), was proposed as an alternative to cross validation for selecting network complexity. I...
A serious drawback of kernel methods, and Support Vector Machines (SVM) in particular, is the difficulty in choosing a suitable kernel function for a given dataset. One of the appr...
Huyen Do, Alexandros Kalousis, Adam Woznica, Melan...
Discriminative approaches to human pose inference involve mapping visual observations to articulated body configurations. Current probabilistic approaches to learn this mapping ha...