Memory as transformation: LETHE, a self-referential gan-inspired architecture
Memory as transformation: LETHE, a self-referential gan-inspired architecture
记忆即转化：LETHE，一种受 GAN 启发的自指架构
Abstract: 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.
摘要： LETHE（基于时间分层准平衡的潜在参数演化）是一个在 SuperCollider 中实现的自指式“声音遗忘”系统。它采用了生成对抗网络（GAN）的形式化词汇，并在初始化后无需外部数据集或监督的封闭配置下运行。
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.
音频由一个围绕两条延迟线构建的 3 x 3 混合矩阵进行处理；其九个系数和两个延迟时间通过一个五特征线性判别器与类似于单样本 REINFORCE 的随机扰动优化器之间的交互而演化。判别器将当前的能量行为与初始状态的存档进行比较，并指导参数更新。
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 ($\Delta c_{22}=0.000$ 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.
循环源、固定源和实时源可以独立混合。在包含消融对照的固定和循环会话中，主动生成器对于参数演化是必不可少的（在所有 15 次消融会话中 $\Delta c_{22}=0.000$）。LETHE 置身于自指电声音乐的传统之中，将声音结果委托给一个自适应闭环，其参数空间由作曲家定义。