Pro Audio Source Separation vs GPU Audio SDK Module

YouTube.com/watch?v=QMZBlEc9Vhc

GPU Audio have a new SDK Module to share with you. Our Source Separation Module is available now as part of our SDK, find all the details here: https://gpu.audio/sdk

In this video we take a look at what Source Separation is, then compare it to the best non-realtime platforms, then to the leading Real-time Source Separation software. We also cover some use cases for the module - which is not limited to any one application. The machine used for this demo is an NVIDIA 4090 Desktop.

Overview of the Technology
Start by reviewing the motivation and core principles behind our technology here: https://github.com/gpuaudio/gpuaudio-sdk?tab=readme-ov-file#motivation-and-introduction

1. SDK Installation
Download and install the SDK by following the instructions here: https://github.com/gpuaudio/gpuaudio-sdk/blob/main/installation/main.md

2. Build Initial Example Projects
We recommend beginning with simple examples such as the Gain and FIR processors to verify your setup: https://github.com/gpuaudio/gpuaudio-sdk?tab=readme-ov-file#example-projects

3. Evaluate a Target Module (Realtime Source Separation – HSTasNet)
For example, you can test realtime source separation based on the HSTasNet neural network:
https://github.com/gpuaudio/gpuaudio-sdk?tab=readme-ov-file#real-time-sound-source-separation-rt3s

Please make sure to test this module within your DAW environment by building it as a plugin (details here): https://github.com/gpuaudio/gpuaudio-sdk/blob/main/installation/main.md#use-plugins-with-gpu-acceleration-in-the-daw-1

For a detailed technical explanation of how we re-implemented HSTasNet using the GPU Audio Platform, please refer to: https://github.com/gpuaudio/gpuaudiosdk/blob/main/Guides/RealtimeSourceSeparation.pdf

Performance Results - Using the following configuration:
STFT size: 1024
Overlap: 512 samples
Sample rate: 44.1 kHz
Buffer size: 512 samples.

We observed the following realtime ratios (RTR - how many times faster than real time the system processes one audio buffer):

CPU version (Eigen): 0.18× RTR = ~5x times slower than realtime
Meta PyTorch (GPU): 0.58× RTR = can't process one buffer on time still
GPU Audio SDK: 6.95× RTR ?.

This represents approximately:
~12× performance improvement over standard GPU (PyTorch) ?
~36× performance improvement compared to CPU implementation ?.

The GPU Audio SDK is free to download here: https://gpu.audio/sdk