Learn More
Hidden Markov model speech recognition systems typically use Gaussian mixture models to estimate the distributions of decor-related acoustic feature vectors that correspond to individual sub-word units. By contrast, hybrid connectionist-HMM systems use discriminatively-trained neural networks to estimate the probability distribution among subword units(More)
Hidden Markov model speech recognition systems typically use Gaussian mixture models to estimate the distributions of decor-related acoustic feature vectors that correspond to individual sub-word units. By contrast, hybrid connectionist-HMM systems use discriminatively-trained neural networks to estimate the probability distribution among subword units(More)
We evaluate the performance of several feature sets on the AURORA task as defined by ETSI. We show that after a non-linear transformation, a number of features can be effectively used in a HMM-based recognition system. The non-linear transformation is computed using a neural network which is discriminatively trained on the phonetically labeled (forcibly(More)
OBJECTIVE While corner store-based nutrition interventions have emerged as a potential strategy to increase healthy food availability in low-income communities, few evaluation studies exist. We present the results of a trial in Baltimore City to increase the availability and sales of healthier food options in local stores. DESIGN Quasi-experimental study.(More)
BACKGROUND Existing evidence indicates that Inuit in Arctic Canada are undergoing a lifestyle transition leading to decreased physical activity (PA) and increased body mass index (BMI). Data specific to PA and BMI amongst Inuit in Nunavut, Canada, are currently limited. The present study aimed to characterise current PA and BMI levels in a sample of Inuit(More)
Obesity and other diet-related chronic diseases are more prevalent in low-income urban areas, which commonly have limited access to healthy foods. The authors implemented an intervention trial in nine food stores, including two supermarkets and seven corner stores, in a low-income, predominantly African American area of Baltimore City, with a comparison(More)
The mutual information concept is used to study the distribution of speech information in frequency and in time. The main focus is on the information that is relevant for phonetic classiication. A large database of hand-labeled uent s p e e c h is used to (a) compute the mutual information (MI) between a phonetic classiication variable and one spectral(More)
BACKGROUND Accurate nutrient composition data for composite dishes unique to a population is essential for the development of a nutrient database and the calculation of dietary intake. The present study aimed to provide the nutritional composition of composite dishes frequently consumed in rural KwaZulu-Natal, South Africa. METHODS Commonly consumed(More)