拟声词光标：用漫画风格字体对鼠标移动进行言语镜像
Onomatopoeia Cursor: Verbal Mirroring of Mouse Movement with Comic-Style Lettering
浏览论文内容
中文总结 AI 辅助
本文提出拟声词光标系统，实时分类鼠标运动并渲染日语拟声词漫画字体，通过形态生成器和轻量变压器合成新词，探讨言语镜像对动作能动感的影响。
中文摘要 AI 辅助
鼠标光标半个世纪以来在视觉上一直保持沉默：它显示我们指向哪里，却对我们如何移动只字不提。我们提出了拟声词光标，一个已发布的macOS覆盖层，它实时分类光标运动学，并在光标上方以动画漫画风格字体渲染日语拟声词——快速水平反转时显示“kyorokyoro”（四处张望），缓慢谨慎移动时显示“sorosoro”（小心翼翼地），快速直线移动时显示“byuun”（嗖的一声）。该系统读取七个输入通道，并以五种语言显示约六十种词形。关键在于，每个词的形式通过一个基于日语声音象征（浊音=重量，促音=突然性，长音=程度，叠词=重复）的形态生成器，随动作方式而波动。在规则生成器之外，一个仅处理拟声词的设备端变压器（0.4M参数，每个词9.7毫秒）在2,782个拟声词上训练，从动作方式合成新词形；对于声音明确的事件，一个家族锚定生成器将合成限制在正确的语音家族内。字符通过手绘轮廓扰动、笔刷风格变形和基于漫画字体惯例的逐字符动画进行渲染。我们阐述了言语运动镜像的设计空间，将流程形式化为可学习的可微映射，并报告了对实际实现和测量内容的技术评估。我们的核心猜想涉及能动感：形成性的第一人称使用表明，在动作发生时对其进行命名会扰动该动作的归属感——调制、放大和干扰——我们概述了一项具有显著性匹配对照的受试者内研究作为未来工作。我们不声称任何用户研究结果；贡献在于概念、工作系统及其设计空间。
英文摘要
The mouse cursor has remained visually mute for half a century: it shows where we point, but says nothing about how we move. We present the Onomatopoeia Cursor, a shipped macOS overlay that classifies cursor kinematics in real time and renders Japanese mimetic words (onomatopoeia) as animated comic-style lettering above the cursor -- "kyorokyoro" (glancing around) for rapid horizontal reversals, "sorosoro" (cautiously) for slow careful motion, "byuun" (whoosh) for fast straight strokes. The system reads seven input channels and displays roughly sixty word forms across five languages. Crucially, the form of each word fluctuates with the manner of action through a morphological generator grounded in Japanese sound symbolism (voicing = weight, gemination = abruptness, elongation = extent, reduplication = iteration). Beyond the rule generator, an on-device onomatopoeia-only transformer (0.4M parameters, 9.7 ms per word) trained on 2,782 mimetic words synthesizes novel forms from the manner of an action; for sound-definite events, a family-anchored generator constrains synthesis to the correct phonetic family. Characters are rendered with hand-drawn outline perturbation, brush-style deformation, and per-character animation grounded in manga lettering conventions. We articulate the design space of verbal motion mirroring, formalize the pipeline as a learnable differentiable mapping, and report a technical evaluation of what is actually implemented and measured. Our central conjecture concerns the sense of agency: formative first-person use suggests that naming a movement while it happens perturbs the felt authorship of the action -- modulation, amplification, and interference -- and we outline a within-subjects study with salience-matched controls as future work. No user-study results are claimed; the contribution is the concept, the working system, and its design space.
发表机构
- University of Tsukuba（筑波大学）
机构由 AI 辅助整理，请以论文原文为准。
