用自参考机制让声音随时间演化，无需外部数据
Memory as transformation: LETHE, a self-referential gan-inspired architecture
- 基于对抗网络思想构建闭环系统，参数由内部反馈自适应更新
- 9个混音系数与2个延迟时间随时间持续演化，驱动声音变化
- 适合探索无监督声景生成的作曲家与实验音乐创作者
LETHE（潜在参数随时间分层准平衡演化）是一种在SuperCollider中实现的自参考声学消亡系统。其采用生成对抗网络的形式语言，在初始化后不依赖外部数据或监督信号。音频通过一个围绕两条延迟线构建的3×3混音矩阵处理，九个系数和两个延迟时间由五维线性判别器与类单样本REINFORCE的随机扰动优化器共同驱动演化。判别器将当前能量行为与初始状态存档进行比较，指导参数更新。固定、循环及实时源可独立混合。在固定与循环会话中，经消融控制验证，活跃生成器对参数演化至关重要（15次消融实验中Δc₂₂=0.000）。该系统延续自参考电子声学音乐传统，将声音结果交由自适应闭环决定，其参数空间由作曲者定义。
原文摘要 · Abstract (English)
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 ($\Delta c_{22}=0.000$ 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.
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。