1P1-E16 教示者の音韻情報と唇の形状を利用したロボットの音韻獲得

概要

論文の詳細を見る
A pioneering constructivist approach to building a robot that reproduces a developmental process of infants' vowel acquisition has been conducted by Yoshikawa et al. inspired by the observation in infant study. They have constructed a mot her-infant interaction model with robot learning capability and parrot-like teaching by caregiver. However, the robot has not listened his/her own voice, therefore nor actively explored more natural vowels similar to the caregiver. The study presented in this paper extends the previous work in the following manners seeking for more natural interaction. First, imitation of the caregiver's lip. Second, utilizing the pentagon which the caregiver's vowels construct in the formant space. Third, hypothesizing that mutual imitation between the robot and the caregiver is introduced to obtain more natural vowels. Through this process, the desired formants are gradually shifted, expecting to more natural ones. The experimental results are shown and the future issues are discussed.
一般社団法人日本機械学会の論文