Methods of Efficiently Constructing Text-Dialogue-Agent System Using Existing Anime Character

Many surely dream of being able to chat with his/her favorite anime characters from an early age. To make such a dream possible, we propose an efficient method for constructing a system that enables users to text chat with existing anime characters. We tackled two research problems to generate verbal and nonverbal behaviors for a text-chat agent system of an existing character. In the generation of verbal behavior, it is a major issue to be able to generate utterance text that reflects the personality of existing characters in response to any user questions. For this problem, we propose the use role play-based question-answering to efficiently collect high-quality paired data of user’s questions and system’s answers reflecting the personality of an anime character. We also propose a new utterance generation method that uses a neural translation model with the collected data. Rich and natural expressions of nonverbal behavior greatly enhance the appeal of agent systems. However, not all existing anime characters move as naturally and as diversely as humans. Therefore, we propose a method that can automatically generate whole-body motion from spoken text in order to make it so that anime characters have human-like and natural movements. In addition to these movements, we try to add a small amount of characteristic movement on a rule basis to reflect personality. We created a text-dialogue agent system of a popular existing anime character using our proposed generation methods. As a result of a subjective evaluation of the implemented system, our models for generating verbal and nonverbal behavior improved the impression of the agent’s responsiveness and reflected the personality of the character. In addition, generating characteristic motions with a small amount of on the basis of heuristic rules was not effective, but rather the character generated by our generation model that reflects the average motion of persons had more personality. Therefore, our proposed methods for generating verbal and nonverbal behaviors and the construction method will greatly contribute to the realization of text-dialogue-agent systems of existing characters.