AI 中文总结
该研究提出在SuperCollider中实现的自指声音隐匿系统LETHE，其基于GAN构建封闭无监督配置，通过判别器与优化器交互演化参数，可混合多类声源，为自指电声音乐提供自适应闭环方案。
AI 中文摘要
LETHE（Latent-parameter Evolution with Temporal Hierarchical quasi-Equilibrium，即具有时间分层准平衡的潜参数演化）是一种在SuperCollider中实现的自指声音隐匿系统。它采用生成对抗网络（GAN）的形式化词汇，初始化后处于无外部数据集或监督的封闭配置中。音频由围绕两条延迟线构建的3×3混合矩阵处理；其9个系数和2个延迟时间通过五特征线性判别器与类似单样本REINFORCE的随机扰动优化器的交互演化。判别器将当前能量行为与初始状态存档进行比较，并指导参数更新。循环、固定和实时声源可独立混合。在带消融控制的固定和循环会话中，活动生成器是参数演化所必需的（15次消融会话中Δc₂₂均为0.000）。LETHE植根于自指电声音乐传统，将声音结果委托给由作曲家定义参数空间的自适应闭环。
英文摘要
LETHE (Latent-parameter Evolution with Temporal Hierarchical quasi-Equilibrium) is a self-referential sonic-oblivion system implemented in SuperCollider. It adopts the formal vocabulary of Generative Adversarial Networks in a closed configuration without external datasets or supervision after initialization. Audio is processed by a 3 x 3 mixing matrix built around two delay lines; its nine coefficients and two delay times evolve through the interaction of a five-feature linear discriminator and a random-perturbation optimizer analogous to single-sample REINFORCE. The discriminator compares current energy behavior with an archive of the initial state and guides parameter updates. Circular, fixed, and live sources can be mixed independently. Across fixed and circular sessions with an ablation control, the active generator is necessary for parametric evolution ($Δc_{22}=0.000$ in all 15 ablation sessions). Situated in the tradition of self-referential electroacoustic music, LETHE delegates the sonic outcome to an adaptive closed loop whose parametric space is defined by the composer.
CommentsAccepted at XXV CIM - Colloquio di Informatica Musicale, L'Aquila, 2026
