João Felipe Santo

Research engineer

Tone 3000

About Me

In his latest role at Tone3000, João helped develop A2, a new architecture for Neural Amp Modeler, and optimize implementations in various embedded CPUs. He was previously with NVIDIA, where he did research on several speech and music-related projects, including speech synthesis models, Fugatto and Music Flamingo. He is a DSP engineer and AI researcher with a PhD in deep learning applied to speech processing at Institut National de la Recherche Scientifique (Montréal, Canada).

Sessions

  • Audio ML on Bare Metal

    GEMM, Memory Layout, and Real-Time Dataflow on Embedded ARM
    10:00 - 10:50 UTC | Wednesday 11th November 2026 | Bristol 2
    Advanced

    Audio hardware built around classical DSPs and embedded CPUs (guitar amps, pedals, synths) wasn't designed with machine learning in mind. Yet, Neural Amp Modeler (NAM) can be made to run on the ubiquitous ARM Cortex-M7 at 2x real-time, and models with hundreds of parameters can be trained in tens of milliseconds on the RP2350, a £1 chip. This talk is all about taking a trained model and getting it to run in real time on hardware that has no NPU and no GPU. The core of any ML model is the General Matrix Multiply (GEMM), but on these chips the […]