论文解读

当打击乐手拿起鼓刷:用持续手势对抗鼓机映射的技术俘获

本研究通过与职业鼓手四个月的协同设计,将仅支持离散打击检测的映射扩展为连续手势 RNN 与离散分类协同的 Max4Live 工具包,并以十首曲目录制检验其在真实创作中能否抵御技术俘获,代价是连续特征时域精度与循环稳定性仍有限。

 · 更新于 2026-11-05 · 约 22 分钟 · 10805 字 阅读 →
论文解读

听错一个字就全盘皆输:SpeechGym 把语音智能体的失败变成可训练的梯度

语音交互 | 7.6/10

 · 更新于 2026-11-05 · 约 17 分钟 · 8505 字 阅读 →
论文解读

Dancing Through Soundscapes: Designing a Low-Cost, Sound-Based Device for Sensing and Interpreting Movement and Dance

音频交互 | 5.2/10

 · 更新于 2026-11-05 · 约 11 分钟 · 5265 字 阅读 →
论文解读

MultiVerse: A Creator-Centered Approach to Steering Context-Adaptive Lyrics

音乐生成 | 5.4/10

 · 更新于 2026-11-05 · 约 12 分钟 · 5817 字 阅读 →
论文解读

DIY e-HandPan: A new DIY Low-Cost Handpan Interface based on Arduino and ESP32 Microcontrollers

音频交互 | 7.2/10

 · 更新于 2026-11-05 · 约 13 分钟 · 6288 字 阅读 →
论文解读

Dramarrator: Object-Based Audio Editing for Audio Drama Production from Books

音频生成 | 7.0/10

 · 更新于 2026-11-05 · 约 14 分钟 · 6691 字 阅读 →
论文解读

Beyond Call and Response: Modelling Reciprocal Coordination in Human-AI Vocal Ensembles

歌唱生成 | 5.5/10

 · 更新于 2026-11-05 · 约 11 分钟 · 5433 字 阅读 →
论文解读

Deep Learning for Real-Time Sound Order Recognition in Human-Robot Interaction

音频事件检测 | 5.2/10

 · 更新于 2026-11-05 · 约 11 分钟 · 5506 字 阅读 →
论文解读

Embodied Empathy: A Multimodal AR and LLM-Powered System for Self-Attachment Psychotherapy with Self-Initiated Humour

音频交互 | 5.4/10

 · 更新于 2026-11-05 · 约 13 分钟 · 6236 字 阅读 →
论文解读

Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis

音频交互 | 7.0/10

 · 更新于 2026-11-05 · 约 14 分钟 · 6613 字 阅读 →