著者

鍵谷 龍樹 白川 由貴 土斐崎 龍一 渡邊 淳司 丸谷 和史 河邉 隆寛 坂本 真樹

出版者

人工知能学会

雑誌

人工知能学会全国大会論文集 (ISSN:13479881)

巻号頁・発行日

vol.28, 2014

---

本研究では,粘性情報を持つ動画・静止画がどのようなオノマトペの音韻によって表されるかを調べ,粘性に関連する運動情報、形態情報に特徴的な音韻を特定した.その結果を利用することで粘性を表す映像を対象とし,「ドロドロした動画を欲しい」という直観的な要望を叶える粘性映像推奨システムを実現可能である.

著者

鍵谷 龍樹 白川 由貴 土斐崎 龍一 渡邊 淳司 丸谷 和史 河邉 隆寛 坂本 真樹

出版者

一般社団法人 人工知能学会

雑誌

人工知能学会論文誌 (ISSN:13460714)

巻号頁・発行日

vol.30, no.1, pp.237-245, 2015-01-06 (Released:2015-01-06)

参考文献数

25

被引用文献数

1

---

We feel some liquids such as honey or oil more viscous than others like water. Viscosity perception is frequently expressed by onomatopoeia, a set of words that are often used to express sensory experiences in Japanese. For example, we would say honey is “toro-toro” or oil is “doro-doro”. In this paper we investigated the associations between phonemes of Japanese onomatopoeia for expressing viscosity and subjective evaluations of viscosity. Specifically, we performed psychological experiments where participants watched some static images and dynamic images. Participants were asked to express the visual sensations by onomatopoeia and rate the degree to which they felt the objects viscous. This experiment was aimed at specifying the systematic association between phonemes of Japanese onomatopoeic words and viscous evaluations. Our results showed the existence of some associations between the phonemes of the words for expressing the sensation and the evaluations of viscosity and showed the possibility to construct a system to recommend viscosity animations by onomatopoeia. The system proposed in this paper recommends viscosity animations consistent with onomatopoetic expressions based on Japanese sound symbolism. Our system comprises a user interface module, an onomatopoeia parsing module, and a database. Our system can evaluate the subtle difference in viscosity feelings expressed by onomatopoeic words which are different in phonemes.