The use of speech production knowledge and data to enhance speech recognition is being actively pursued by a number of widely dispersed research groups using different approaches. The goal of this workshop is to bring together these research groups, as well as other researchers who are interested in learning about or contributing ideas to this area, to share ideas, results, and perspectives in an intimate and productive setting. The range of techniques currently being explored is rapidly growing, and is increasingly benefiting from new ideas in machine learning and availability of data, making this a particularly good time for such a workshop.
The workshop will feature a series of talks and general submissions. Submissions focusing on novel research, review papers, and position papers are solicited. Topics of interest include speech production models in speech recognition, the collection and use of speech production data, acoustic-to-articulatory inversion, silent speech interfaces, and the use of speech production in related areas such as speech synthesis and voice conversion.