Abstract It is widely believed among speech and language researchers that the incorporation of linguistic information should improve statistical models of natural language and benefit applications such as speech recognition. This belief has yet to[…]
Abstract To establish better paradigms for automated speech recognition may take new science. On the other hand, if we assume that speech operates within the same neural framework that governs other sensorimotor processes, then there[…]
Abstract An unconventional view of speech reveals a distinctly phonetic module at the level of action and perception. That such a module exists can be defended on grounds of plausibility and by the weight of[…]
Abstract Despite significant progress in speech recognition technology over the last 20 years, we sometimes observe results that do not match our preconceptions. Of course, this is often due to poor design or buggy code.[…]
Abstract Routing and filtering are terms used to describe the process of comparing text streams (such as newswire feeds) to the appropriate users. Although similar to the task of information retrieval, there are significant differences[…]
Abstract I will describe a novel technique for constructing a subcategorization dictionary from textual corpora. Each dictionary entry encodes the relative frequency of occurrence of a comprehensive set of subcategorization classes for English. An initial[…]
Abstract This paper presents three-dimensional tongue surfaces reconstructed from sixty cross-sectional slices of the tongue. Surfaces were reconstructed for sustained vocalizations of 18 American English sounds. Electropalatography (EPG) data also were collected for the sounds[…]
