Abstract This talk is concerned with the design of algorithms for finding clusters in high-dimensional space. We develop and implement a clustering algorithm appropriate for problems in which a small number of observations are embedded[…]
Research Groups tAutomatic Learning of Word Pronunciation from Data tDependency Modeling tModeling Systematic Variations in pronunciation Modeling via a Language-Dependent Hidden Speaking Mode tSpeech Data Modeling
Abstract As studies in echo-locating bat have taught us how the brain processes sonar signals, our understanding of cortical processing of communication sounds in nonhuman primate models can provide invaluable insights into brain mechanisms underlying[…]
Abstract Advances in speech recognition over the last 20 years have been heavily driven by three factors: more data, more computation, and lots of competition. This talk will describe how these factors have driven the[…]
Abstract Maximum entropy / minimum divergence modeling is a powerful technique for constructing probability models, which has been applied to a wide variety of problems in natural language processing. A maximum entropy / minimum divergence[…]
Abstract I will report on a new method for studying the language processing strategies of children, in which a head-mounted eye tracking system was used to monitor eye movements as children responded to spoken instructions.[…]
Research Groups Core Natural Language Processing Technology Applicable to Multiple Languages Dynamic Segmental Models of Speech Coarticulation Rapid Speech Recognizer Adaptation for New Speakers
