Towards Natural Head Movement of Autonomous Speaker Agent
نویسندگان
چکیده
Autonomous Speaker Agent (ASA) is a graphically embodied animated agent capable of reading plain English text and rendering it in a form of speech, accompanied by appropriate, natural-looking facial gestures [1]. This paper is focused on improving ASA’s head movement trajectories in order to achieve facial gestures that look as natural as possible. Based on the gathered data we proposed mathematical functions that, using two input parameters (maximum amplitude and duration of the gesture) generate natural-looking head motion trajectory. Proposed functions were implemented in our existing ASA platform and we compared them with our previous head movement models. Our results were shown to a larger number of people. The audience noticed that results showed improvement in head motion and didn't detect any patterns which would suggest that animation was done with predefined motion trajectories.
منابع مشابه
Autonomous Speaker Agent
Autonomous Speaker Agent is a graphically embodied animated agent (a virtual character) capable of reading plain English text and rendering it in a form of speech, accompanied by the appropriate, natural-looking facial gestures. The system uses lexical analysis and statistical models of facial gestures in order to generate the gestures related to the spoken text. It is intended for the automati...
متن کاملA Context-aware Architecture for Mental Model Sharing through Semantic Movement in Intelligent Agents
Recent studies in multi-agent systems are paying increasingly more attention to the paradigm of designing intelligent agents with human inspired concepts. One of the main cognitive concepts driving the core of many recent approaches in multi agent systems is shared mental models. In this paper, we propose an architecture for sharing mental models based on a new concept called semantic movement....
متن کاملRecreation of spontaneous non-verbal behavior on a synthetic agent EVA
This paper presents a novel process of transferring the human-generated communicative behavior onto an embodied conversational agent. The aim of our work is to build a high-resolution motion dictionary based on empirical analysis of non-verbal behavior performed in multi-speaker informal dialogues. The verbal and non-verbal behavior is recreated by using this motion dictionary and on pure, unpr...
متن کاملAudio-Visual Correlation Modeling for Speaker Identification and Synthesis
This thesis addresses two major problems of multimodal signal processing using audiovisual correlation modeling: speaker recognition and speaker synthesis. We address the first problem, i.e., the audiovisual speaker recognition problem within an open-set identification framework, where audio (speech) and lip texture (intensity) modalities are fused employing a combination of early and late inte...
متن کاملMultisensory Integration With a Head-Mounted Display: Background Visual Motion and Sound Motion
OBJECTIVE The aim of this study was to assess how background visual motion and the relative movement of sound affect a head-mounted display (HMD) wearer's performance at a task requiring integration of auditory and visual information. BACKGROUND HMD users are often mobile. A commercially available speaker in a fixed location delivers auditory information affordably to the HMD user. However, p...
متن کامل