Virtual talking heads and ambiant face-to- face communication
نویسندگان
چکیده
. We describe here our first effort for developing a virtual talking head able to engage a situated face-to-face interaction with a human partner. This paper concentrates on the low-level components of this interaction loop and the cognitive impact of the implementation of mutual attention and multimodal deixis on the communication task.
منابع مشابه
Texture-based Expression Modelling for a Virtual Talking Head
The human face plays a vital role in everyday human-to-human communication as it has the capability of conveying a vast amount of different social, emotional and conversational cues, which influence the meaning and the flow of interaction. Of particular importance is the ability of the face to express inner emotional states, such as emotions of happiness and anger, through different facial expr...
متن کاملA Tool for Simplified Creation of MPEG4-Based Virtual Talking Heads
The aim of this master’s thesis was to develop a tool for easier creation of animated talking heads, using the latest animation platform developed at the department of Speech, Music and Hearing at KTH. This animation platform is based on the new, international MPEG4standard for faceand body animation and it allows for arbitrary static face models to be animated and used for speech synthesis. To...
متن کاملPrevis: a person-specific realistic virtual speaker
This paper describes a 2D realistic talking face. The facial appearance model is constructed with a parameterised 2D sample based model. This representation supports moderated head movements, facial gestures and emotional expressions. Two main contributions for talking heads applications are proposed. First, the image of the lips is synthesized by means of shape and texture information. Secondl...
متن کاملReal Face Communication in a Virtual World
This paper describes an efficient method to make an individual face for animation from several possible inputs and how to use this result for a realistic talking head communication in a virtual world. We present a method to reconstruct 3D facial model from two orthogonal pictures taken from front and side views. The method is based on extracting features from a face in a semiautomatic way and d...
متن کاملExploring the Uncanny Valley Effect with talking heads
Here the “Uncanny Valley”, where falling just short of perfection in creating synthetic humans exacts a large negative reaction, is explored with talking head animations focusing on naturalness in speech, face model and face motion. We discuss possible techniques to manipulate naturalness for each of these aspects. Outcomes of this method will provide insights for the choice of the degree of re...
متن کامل