Document Type

Technical Report

Department

Computer Science and Engineering

Publication Date

1993-01-01

Filename

WUCS-93-33.PDF

Technical Report Number

WUCS-93-33

Abstract

The analysis of human conversations has revealed that the design of interfaces using spoken dialogue must differ radically from those using written communication. Such characteristics as prosody, confirmations, echoes, and other speech phenomena must be considered. This work is a step in that direction. Prosodic, syntactic and semantic information from actual human dialogues has been used to build a turn-taking model empirically for dydadic telephone dialogues. The ability to predict completion of turns has been the biggest motivating factor in the development of this model. The design and evaluation of the model are presented in this report.

Comments

Permanent URL: http://dx.doi.org/10.7936/K7Q52MTF

WUCS-93-33-2.pdf (935 kB)

Share

COinS