4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Modeling Contrast in the Generation and Synthesis of Spoken Language

Scott Prevost

The Media Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA

This paper presents an implemented model of spoken language processing that accounts for intonational phenomena associated with semantic contrasts. The model determines accentual patterns based on sets of alternative properties from a knowledge base and a contrastive stress algorithm. The results of applying the model to a natural language generation program illustrate the advantages over previous models based on lexical "givenness."

Full Paper   Sound Example #1   Sound Example #2

Bibliographic reference.  Prevost, Scott (1996): "Modeling contrast in the generation and synthesis of spoken language", In ICSLP-1996, 1349-1352.