Discriminative speech processing techniques attempt to compute the maximum a posterior probability of some speech event, such as a particular phoneme being spoken, given the observed data. Non-discriminative techniques compute the likelihood of the observed data assuming an event. Non-discriminative methods such as simple HMMs (hidden Markov models) achieved success despite their lack of discri...

This paper describes our approach to developing novel vector based measures of semantic similarity between a pair of sentences or utterances. Measures of this nature are useful not only in evaluating machine translation output, but also in other language understanding and information retrieval applications. We first describe the general family of existing vector based approaches to evaluating s...

INTRODUCTION Analysis of nuclear texture features as a measure of nuclear chromatin changes has been proven to be useful when measured on thin (5-6 microm) tissue sections using conventional 2D bright field microscopy. The drawback of this approach is that most nuclei are not intact because of those thin sections. Confocal laser scanning microscopy (CLSM) allows measurements of texture in 3D re...

Rent-seeking behavior by participants in payment for environmental services auctions reduces the number of affordable contracts and decreases environmental protection. I propose a new auction mechanism, the provision point reverse auction (PPRA), to mitigate this rent-seeking behavior. The PPRA includes a public component where the probability of contract acceptance for one individual is affect...

Extreme Learning Machine (ELM), which was initially proposed for training single-layer feed-forward networks (SLFNs), provides us a unified efficient and effective framework for regression and multiclass classification. Though various ELM variants were proposed in recent years, most of them focused on the supervised learning scenario while little effort was made to extend it into unsupervised l...

Discriminative fear conditioning requires learning to dissociate between safety cues and cues that predict negative outcomes yet little is known about what processes contribute to discriminative fear learning. According to attentional models of time perception, processes that distract from timing result in temporal underestimation. If discriminative fear learning only requires learning what cue...

fMPE is a previously introduced form of discriminative training, in which offsets to the features are obtained by training a projection from a high-dimensional feature space based on posteriors of Gaussians. This paper presents recent improvements to fMPE, including improved high-dimensional features which are easier to compute, and improvements to the training procedure. Other issues investiga...