Paper: Constituent-based Accent Prediction

ACL ID P98-2155
Title Constituent-based Accent Prediction
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1998

Near-perfect automatic accent assignment is at- tainable for citation-style speech, but better com- putational models are needed to predict accent in extended, spontaneous discourses. This paper presents an empirically motivated theory of the dis- course focusing nature of accent in spontaneous speech. Hypotheses based on this theory lead to a new approach to accent prediction, in which pat- terns of deviation from citation form accentuation, defined at the constituent or noun phrase level, are atttomatically learned from an annotated cor- pus. Machine learning experiments on 1031 noun phrases from eighteen spontaneous direction-giving monologues show that accent assignment can be significantly improved by up to 4%-6% relative to a hypothetical baseline system that wotdd produce only citat...