Emotional Variation in Speech-Based Natural Language Generation

A framework for handling emotional variations in a speech-based natural language system for use in the MRE virtual training environment and cast the problem of emotional generation as a distance minimization task, in which the system chooses between multiple valid realizations for a given input based on the emotional distance of each realization from the speaker’s attitude toward that input.

Abstract

We present a framework for handling emotional variations in a speech-based natural language system for use in the MRE virtual training environment. The system is a first step toward addressing issues in emotion-based modeling of verbal communicative behavior. We cast the problem of emotional generation as a distance minimization task, in which the system chooses between multiple valid realizations for a given input based on the emotional distance of each realization from the speaker’s attitude toward that input. Emotional Variation in Speech-Based Natural Language Generation Michael Fleischman and Eduard Hovy USC Information Science Institute 4676 Admiralty Way Marina del Rey, CA 90292-6695 U.S.A. {fleisch, hovy} @ISI.edu Abstract We present a framework for handling emotional variations in a speech-based natural language system for use in the MRE virtual training environment. The system is a first step toward addressing issues in emotion-based modeling of verbal communicative behavior. We cast the problem of emotional generation as a distance minimization task, in which the system chooses between multiple valid realizations for a given input based on the emotional distance of each realization from the speaker’s attitude toward that input. We discuss evaluations of the system and future work that includes modeling personality and empathy within the same framework.We present a framework for handling emotional variations in a speech-based natural language system for use in the MRE virtual training environment. The system is a first step toward addressing issues in emotion-based modeling of verbal communicative behavior. We cast the problem of emotional generation as a distance minimization task, in which the system chooses between multiple valid realizations for a given input based on the emotional distance of each realization from the speaker’s attitude toward that input. We discuss evaluations of the system and future work that includes modeling personality and empathy within the same framework.