| Presentation | 2022-12-23 Detecting emotion in speech expressing incongruent emotional cues through voice and content Mariko Kikutani, Machiko Ikemoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This research investigated how we detect emotion in speech when the emotional cues in the sound of voice do not match the semantic content. In the authors’ previous research, Japanese participants heard a voice emoting anger, happiness or sadness while saying “I’m angry”, “I’m pleased” or “I’m sad”. They reported how much they agree that the speaker is expressing each of the three emotions. Among the three emotions, voice was most important for perception of sadness. For anger and happiness perception, the participants prioritized the information from contents. Based on this study, the present research was conducted by adding facial expressions to those incongruent voice stimuli. The facial expression for each stimulus matched either of the emotion expressed in the voice or content. Even with facial expressions, the perception of anger and happiness prioritized emotional information available in content than voice. However, sadness perception relied more on voice emotion. Importantly, the magnitude of the impact of facial expression was not different depending on which modality, voice or content, showed the same emotion as the face. Participants perceived stronger extent of emotion from stimuli in which the content and face showed the same emotion than from those in which the voice and face showed the same emotion. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | emotion / modality / incongruent expression / language |
| Paper # | HIP2022-69 |
| Date of Issue | 2022-12-15 (HIP) |
| Conference Information | |
| Committee | HIP |
|---|---|
| Conference Date | 2022/12/22(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Research Institute of Electrical Communication |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Multi-modal, KANSEI information processing, Vision and its application, Lifelong sciences, Human information processing |
| Chair | Yuji Wada(Ritsumeikan Univ.) |
| Vice Chair | Hiroyuki Umemoto(AIST) / Sachiko Kiyokawa(Nagoya Univ.) |
| Secretary | Hiroyuki Umemoto(Kyushu Univ.) / Sachiko Kiyokawa(NICT) |
| Assistant | Ippei Negishi(Kanazawa Inst. of Tech.) / Daisuke Tanaka(Tottori Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Human Information Processing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Detecting emotion in speech expressing incongruent emotional cues through voice and content |
| Sub Title (in English) | Investigation on dominant modality |
| Keyword(1) | emotion |
| Keyword(2) | modality |
| Keyword(3) | incongruent expression |
| Keyword(4) | language |
| 1st Author's Name | Mariko Kikutani |
| 1st Author's Affiliation | KKanazawa University(Kanazawa Univ.) |
| 2nd Author's Name | Machiko Ikemoto |
| 2nd Author's Affiliation | Doshisha University(Doshisha Univ.) |
| Date | 2022-12-23 |
| Paper # | HIP2022-69 |
| Volume (vol) | vol.122 |
| Number (no) | HIP-326 |
| Page | pp.pp.59-64(HIP), |
| #Pages | 6 |
| Date of Issue | 2022-12-15 (HIP) |