Questo sito utilizza cookie di terze parti per inviarti pubblicità in linea con le tue preferenze. Se vuoi saperne di più clicca QUI 
Chiudendo questo banner, scorrendo questa pagina, cliccando su un link o proseguendo la navigazione in altra maniera, acconsenti all'uso dei cookie. OK

Multimodal Distinctive Behavior for Expressive Embodied Conversational Agents

Embodied Conversational Agents are a new type of computer interfaces which have human-like bodies and conversational skills. Users interacting with agents will be more engaged and participative if the agents exhibit behaviors which look coherent across different situations and emotional states.
In the present work, we aim at increasing agents believability by looking at two main aspects of the problem:

- an agent must be able to show its emotional state and communicative intentions not only through specific facial expressions, gestures, etc., but also by varying the quality of its movements (e.g., their speed, amplitude, etc.) and the choice of the modalities that are used to communicate;

- the agent must maintain a distinctive behavior, that is its global behavior tendency has to remain apparent during any communication;

We have developed a model to solve the two above issues. We have evaluated the realism and believability of the resulting agent's behaviors through perceptual tests and application scenario. The resulting system is highly extensible and configurable. It can also be used as a research tool to study human communication.

Mostra/Nascondi contenuto.
Chapter 1 Introduction 1.1 Context Embodied Conversational Agents (ECAs) are a new kind of Human-Computer Interface that are embodied and have conversational skills [24]. They exhibit a human-like aspect, in both appearance and behavior, capable of exhibiting conversational functions, emotional states, personality traits, etc. People in general tend to deal with computers as if they were humans, as stated by Reeves and Nass in their book “The Media Equation” [83]. ECAs promise to increase the quality of communication between humans and computers, as they are designed to communicate and interact in a human-like manner. The first systems implementing ECAs aimed solely at reproducing the basic skills of human-human conversation: ECAs had schematic bodies, exhibited monotonic speech, and produced few and simple gestures and facial expressions. In recent years, developers focused on refining ECAs by modeling key aspects of human-human interaction. Human communication involves verbal and nonverbal behaviors: the words we utter represent the verbal part of communication, while the nonverbal part is constituted 2

Tesi di Dottorato

Dipartimento: Ecole doctorale cognition, langage, interaction

Autore: Maurizio Mancini Contatta »

Composta da 201 pagine.


Questa tesi ha raggiunto 186 click dal 01/10/2008.

Disponibile in PDF, la consultazione è esclusivamente in formato digitale.