Near-perfect automatic accent assignment is attainable f o r citation-style speech, but better computational models are needed to predict accent in extended, spontaneous discourses. This paper presents an empirically motivated theory o f the discourse focusing nature o f accent in spontaneous speech. Hypotheses based on this theory lead to a new approach to accent prediction, in which patterns of deviation from citation form accentuation, defined at the constituent or noun phrase level, are atttomatically learned from an annotated corpus. .
