用超网络生成吉他音色，零样本建模更灵活。
Demo of Zero-Shot Guitar Amplifier Modelling: Enhancing Modeling with Hyper Neural Networks
- 用超网络生成调制参数，实现输入与参考音色的混合。
- 扩展训练数据覆盖更多音色，提升泛化能力。
- 实时插件演示，适合音乐人和音色开发人员使用。
电吉他音色建模通常聚焦于从干净信号到放大器渲染音频的非线性变换。传统方法依赖一对一映射，将设备参数融入神经模型以复现特定放大器，但受限于特定训练数据。本文基于前人工作，采用音色嵌入编码器与特征逐维线性调制（FiLM）条件机制，并改用超网络驱动的门控卷积网络（GCN）作为条件生成器，实现输入信号与参考音频音色特性的融合。通过扩展训练数据覆盖更广泛的放大器音色，模型能够捕捉更丰富的音色表现。此外，我们开发了实时插件，直观展示系统实用性。结果表明，该系统在音色建模多样性上优于传统方法。
原文摘要 · Abstract (English)
Electric guitar tone modeling typically focuses on the non-linear transformation from clean to amplifier-rendered audio. Traditional methods rely on one-to-one mappings, incorporating device parameters into neural models to replicate specific amplifiers. However, these methods are limited by the need for specific training data. In this paper, we adapt a model based on the previous work, which leverages a tone embedding encoder and a feature wise linear modulation (FiLM) condition method. In this work, we altered conditioning method using a hypernetwork-based gated convolutional network (GCN) to generate audio that blends clean input with the tone characteristics of reference audio. By extending the training data to cover a wider variety of amplifier tones, our model is able to capture a broader range of tones. Additionally, we developed a real-time plugin to demonstrate the system's practical application, allowing users to experience its performance interactively. Our results indicate that the proposed system achieves superior tone modeling versatility compared to traditional methods.
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。