AI 中文总结
研究针对WaveNet风格吉他放大器模型计算成本高的问题，提出支持稀疏的推理引擎用于iOS，通过激进剪枝和定制稀疏C++引擎实现实时运行，大幅减少权重且质量无损，能在iPhone上维持低延迟操作。
AI 中文摘要
WaveNet风格的卷积网络能高保真地模拟电子管放大器和失真效果器，但其计算成本使其局限于桌面或专用DSP硬件。我们提出了一种适用于iOS的支持稀疏的WaveNet推理引擎，它能在iPhone上实时运行经过大量剪枝的神经吉他放大器模型。通过激进的迭代幅度剪枝可去除90%的网络权重且质量无明显损失。定制的稀疏C++引擎将这种稀疏性直接转化为计算节省，在仅使用CPU的iPhone实现上维持低延迟实时操作，而密集模型无法做到。设备上的输出与训练模型在int16量化误差内匹配。在演示中，参观者将通过iPhone硬件上的应用弹奏吉他，并将设备上的剪枝模型与它所模拟的物理效果器进行A/B对比。源代码和音频示例可在该https URL获取。
英文摘要
WaveNet-style convolutional networks emulate tube amplifiers and distortion pedals with high fidelity, but their computational cost has confined them to desktops or dedicated DSP hardware. We present a sparse-enabled WaveNet inference engine for iOS that runs heavily pruned neural guitar amplifier models in real time on iPhones. Aggressive iterative magnitude pruning removes 90% of the network weights with no perceptible loss in quality. A custom sparse C++ engine turns this sparsity directly into compute savings, sustaining low-latency real-time operation on a CPU-only iPhone implementation where the dense model cannot. On-device output matches the trained model to within int16 quantization error. At the demonstration, visitors will play a guitar through the app on iPhone hardware and A/B the on-device pruned model against the physical pedal it emulates. Source code and audio examples are available at https://github.com/ryos17/wavenet-imp.
CommentsAccepted to DAFx 2026 Demo
