DesignLex
/人机交互/multimodal
论文进阶

multimodal

多模态,指交互系统同时使用或支持多种感官通道(视觉、听觉、触觉、嗅觉等)进行输入或输出。

English Definition

"Referring to interactive systems that engage multiple sensory channels (visual, auditory, haptic, olfactory, etc.) for input or output."

用法说明 · 针对中文母语者

在 HCI/UX 中 multimodal interaction 强调输入多样(语音+触控+手势等);在 ACI/可访问性领域常指视听触嗅多通道的输出设计。注意与 multimedia(多媒体)区分。

常见错误

  • ·误译为'多模式',应译为'多模态'
  • ·与 multimedia(多媒体)混用

真实用例 · 3

"we developed CreatureConnect, a distributed device with which lemurs and zoo visitors alike can control the intensity of sounds, smells, and visuals on either side of the enclosure boundary."

论文Pipeline extracted — review needed·系统介绍中说明涉及多感官通道

"Below, we review work on multimodal animal technologies and technology-mediated AVIs, alongside how the control assigned and the choice provided mould both."

论文Pipeline extracted — review needed·文献综述章节明确把多模态技术作为讨论主题

"Animal technologies typically apply visual (63.32%) and auditory (27.64%) modes. Though olfactory ones seldom feature (1.01%) [65], they are fundamental to animals' foraging behaviour and therefore warrant deeper investigation."

论文Pipeline extracted — review needed·引述文献中说明多模态在动物技术中的分布
由 pipeline 自动采集,待人工 review