返回全部动态
LETHE：一种自指涉的GAN启发式音频架构
原标题：Memory as transformation: LETHE, a self-referential gan-inspired architecture
AI 摘要
LETHE 是一个在 SuperCollider 中实现的自指涉音频系统，采用 GAN 的正式词汇，但无需外部数据集或监督。它通过一个五特征线性判别器与随机扰动优化器交互，动态调整反馈延迟网络的参数，使音频演化。实验表明，主动生成器对参数演化是必要的，该系统将作曲家的参数空间与自适应闭环结合，延续了自指涉电子音乐的传统。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
MEMORY AS TRANSFORMATION: LETHE, A SELF-REFERENTIAL GAN-INSPIRED ARCHITECTURE 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. Audio is processed by a 33 mixing matrix built around two delay lines; its nine coefficients and two de
发布时间：2026-09-07 12:00
抓取时间：2026-09-07 12:06
来源机构：arXiv