WaveNet-Style Guitar Amplifier Model Pruning for Real-Time iOS Deployment
2026-07-11 • Sound
Sound
AI summaryⓘ
The authors created a way to run complex neural networks that mimic guitar amps and pedals directly on iPhones without needing special hardware. They used a technique called 'pruning' to remove 90% of the network's connections without losing sound quality. This makes the model much faster and able to work in real-time on regular phone processors. They also built a special program to take advantage of the sparse model for efficient computing. People can try the app and compare the sound to real physical pedals.
WaveNetneural networkspruningsparse computationguitar amplifier modelingreal-time inferenceiOSlow-latencyint16 quantization
Authors
Ryota Sato, Eli Silverstein
Abstract
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.