著者

清水 祐一郎 土斐崎 龍一 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.29, no.1, pp.41-52, 2014-01-05 (Released:2014-01-07)

参考文献数

23

被引用文献数

13 6

---

In Japanese, onomatopoeia (i.e., imitative or mimetic words) is frequently used in daily life conversation to express one's intuitive and sensitive feelings. Many onomatopoeic expressions are very similar to each other and their meanings seem to be vague and ambiguous so that it is hard to catch minute semantic differences among onomatopoeic expressions. However, we use onomatopoeia, even novel onomatopoeia, to express our subjective, intuitive and sensitive feelings in daily language use. Therefore, estimating information conveyed by onomatopoeia is inevitable in constructing a human-like intelligent communication system. In this study, we propose a system to estimate information conveyed by onomatopoeia based on Japanese sound symbolism. The existence of synesthetic associations between sounds and sensory experiences (sound symbolism) has been demonstrated over the decades. It is also known that the sensory-sound correspondence can be found not only in words referring to visual shapes, but also in those referring to tactile sensations. So our system quantifies images of inputted onomatopoeia using 43 adjective pair scales related to visual and tactile sensations. Our method hypothesizes that the impression created by an onomatopoeic expression could be predicted by the phonological characteristics of its constituent phonemes. To collect phonemic image data, we conducted a psychological experiment where 78 participants were asked to evaluate the impressions of 312 onomatopoeic expressions, which cover all kinds of Japanese phonemes, against 43 pairs of adjectives in seven-points SD scales. We applied the phonemic image data to our model, and calculated the impression values of each phoneme by making use of a mathematical quantification theory class I. This system estimates rich information conveyed by not only conventional but also newly created onomatopoeic expressions and differentiates among a variety of onomatopoeic expressions, which are frequently similar to each other. We conducted another psychological experiment in order to confirm the effectiveness of our system. Results showed that our system succeeded in evaluating information conveyed by onomatopoeia.

著者

土斐崎 龍一 飯場 咲紀 岡谷 貴之 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.124-137, 2015-01-06 (Released:2015-01-06)

参考文献数

51

被引用文献数

1 1

---

With the widespread use of online shopping in recent years, consumer search requests for products have become more diverse. Previous web search methods have used adjectives as input by consumers. However, given that the number of adjectives that can be used to express textures is limited, it is debatable whether adjectives are capable of richly expressing variations of product textures. In Japanese, tactile and visual textures are easily and frequently expressed by onomatopoeia, such as ``fuwa-fuwa'' for a soft and light sensation and ``kira-kira'' for a glossy texture. Onomatopoeia are useful for understanding not only material textures but also a user's intuitive, sensitive, and even ambiguous feelings evoked by materials. In this study, we propose a system to rank FMD images corresponding to texture associated with Japanese onomatopoeia based on their symbolic sound associations between the onomatopoeia phonemes and the texture sensations. Our system quantitatively estimates the texture sensations of input onomatopoeia, and calculates the similarities between the users' impressions of the onomatopoeia and those of the images. Our system also suggests the images which best match the input onomatopoeia. An evaluation of our method revealed that the best performance was achieved when the SIFT features, the colors of the images, and text describing impressions of the images were used.

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

清水 祐一郎 土斐崎 龍一 鍵谷 龍樹 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.319-330, 2015-01-06 (Released:2015-01-06)

参考文献数

32

被引用文献数

1 2

---

The present study proposes a method which generates Japanese onomatopoeia corresponding to impressions inputted by users. Japanese onomatopoeia is frequently used in comics and advertisements. Effective onomatopoeia in those fields are directly associated with sensuous experiences of readers or consumers, but it is very difficult to create such expressions. Therefore, the system which generates effective novel onomatopoeia corresponding to the impression specified by users has been expected to be as a technology which supports creators. Our system uses 43 SD scales as those expressing our intuitive impressions. These scales consist of scales expressing impressions of a haptic senses, visual senses and affective senses. Users of the system can choose the kinds of SD scales to be used to create onomatopoeia among from 1 to 43 SD scales. The system uses the genetic algorithm (GA) to create onomatopoeia corresponding to inputted impressions. We consider onomatopoeic expressions as a individuals of GA, which are expressed by an array of numerical values. Namely, each numerical value of an individual denotes each phonological symbol in Japanese. By comparing impressions inputted by user with those of each generated onomatopoeia, the system proposes onomatopoeia corresponding to impressions of users. The system evaluation showed that impressions of onomatopoeic expressions generated by our system were similar to the impressions inputted by users.

著者

飯場 咲紀 土斐崎 龍一 坂本 真樹

出版者

特定非営利活動法人 日本バーチャルリアリティ学会

雑誌

日本バーチャルリアリティ学会論文誌 (ISSN:1344011X)

巻号頁・発行日

vol.18, no.3, pp.217-226, 2013

---

We propose a method of recommending colors and fonts appropriate for texts based on the associations between words and colors. Colors and fonts were evaluated by SD scales using affective words in psychological experiments. First, our system estimates colors suitable for the mental representations of the inputted text. Then, the colors are described by affective words. Next, we obtain the degree of similarity between the colors and fonts, whose mental perceptions were evaluated by SD scales in the psychological experiments. Finally, our system recommends colors and fonts that are most appropriate for the inputted text. We verified the validity of our method for selecting appropriate text fonts and colors.

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.

著者

土斐崎 龍一 清水 祐一郎 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.26, 2012

---

毎年約10万件以上の商標が国内で新規登録されており,新奇性のあるブランドネームの開発は年々難しくなっている.本研究は,ブランドネームの音象徴を被験者実験により調査し,ブランドネームが人に喚起する印象の予測値を定量的に出力するシステムを開発した.このシステムを用いることで,ユーザが付加したいイメージに即したブランドネームの提案が可能となり,企業において創造的なブランドネームの開発支援が期待できる.