Richard P. Lippmann

TL;DR: Two approaches were explored which integrate neural net classifiers with Hidden Markov Model (HMM) speech recognizers to improve speech pattern discrimination while retaining the temporal processing advantages of HMMs.

TL;DR: Deploying passive mapping on an enterprise network does not reduce the need for timely active scans due to non-overlapping coverage and potentially long discovery times.

TL;DR: Experiments demonstrated that sigmoid multilayer perceptron (MLP) networks provide slightly better risk prediction than conventional logistic regression when used to predict the risk of death, stroke, and renal failure on 1257 patients who underwent coronary artery bypass operations at the Lahey Clinic.

TL;DR: An HMM-based isolated-word recognition system that dynamically adapts word model parameters to new speakers and to stress-induced speech variations that produces results comparable to multistyle-trained systems.

TL;DR: A new approach to training spotters is presented which computes the Fom gradient for each input pattern and then directly maximizes the FOM using backpropagation, which eliminates the need for thresholds during training.