基于用户评价训练音频转触觉模型，让各种声音都能生成自然触感。
Sound2Hap: Learning Audio-to-Vibrotactile Haptic Generation from Human Ratings
- 用卷积神经网络构建自编码器，从声音直接生成触觉信号。
- 在15人测试中，新方法比传统方法更匹配声音且体验更和谐。
- 适合做智能设备触觉反馈、虚拟现实等需要真实触感的场景。
环境声音如脚步声、键盘敲击声或狗叫声蕴含丰富的信息与情感背景，对用户应用中的触觉设计极具价值。然而，现有音频转振动方法多依赖为音乐或游戏优化的信号处理规则，难以泛化到多样声音。为此，我们首先通过34名参与者对四种算法生成的1000种声音的振动进行评分，发现无明显偏好；基于该数据集，我们训练了Sound2Hap——一个基于CNN的自编码器模型，可低延迟生成符合感知意义的振动。在第二项研究中，15名参与者评价其输出在音振匹配度和触觉体验指数（HXI）上均优于传统信号处理基线，且与多种声音更协调。本工作展示了一种经用户感知验证的音频-触觉转换方法，拓展了声音驱动触觉的应用边界。
原文摘要 · Abstract (English)
Environmental sounds like footsteps, keyboard typing, or dog barking carry rich information and emotional context, making them valuable for designing haptics in user applications. Existing audio-to-vibration methods, however, rely on signal-processing rules tuned for music or games and often fail to generalize across diverse sounds. To address this, we first investigated user perception of four existing audio-to-haptic algorithms, then created a data-driven model for environmental sounds. In Study 1, 34 participants rated vibrations generated by the four algorithms for 1,000 sounds, revealing no consistent algorithm preferences. Using this dataset, we trained Sound2Hap, a CNN-based autoencoder, to generate perceptually meaningful vibrations from diverse sounds with low latency. In Study 2, 15 participants rated its output higher than signal-processing baselines on both audio-vibration match and Haptic Experience Index (HXI), finding it more harmonious with diverse sounds. This work demonstrates a perceptually validated approach to audio-haptic translation, broadening the reach of sound-driven haptics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。