Commercial Software Products
As Founder and Lead Audio Software Developer at Vexon Audio, I design and develop commercial audio software products for musicians, producers, and audio professionals worldwide. These products combine modern C++, JUCE, and advanced DSP techniques, covering the complete product lifecycle from concept and engineering through testing, deployment, and commercial release on macOS and Windows.
Vexon ROAR — Bass Tone Processor
JUCE • C++ • DSP • VST3 • AU • Standalone
Commercial bass enhancement and tone-shaping plugin designed for bass players, producers, and mixing engineers. Features harmonic enhancement, dynamics processing, sub control, and over 40 production-ready presets.
Vexon Lumina — Optical Compressor
JUCE • C++ • DSP • VST3 • AU • Standalone
Modern optical compressor inspired by classic analog workflows, featuring program-dependent compression, character modes, and transparent dynamics control.
Vexon Mirra — Hybrid Convolution Reverb
JUCE • C++ • DSP • VST3 • AU • Standalone
Hybrid reverb processor combining convolution and algorithmic reverb techniques for flexible spatial processing and creative ambience design.
PolyShimmer — Creative Shimmer Reverb
JUCE • C++ • DSP • VST3 • AU • Standalone
Create evolving harmonic spaces with a four-layer shimmer engine and lush Zita-powered ambience. Poly Shimmer transforms guitars, pads, and vocals into cinematic atmospheres.
Audio Technology & Innovation
I specialize in bridging creative music practice with cutting-edge technology. My work combines digital signal processing (DSP), AI-driven sound modeling, and plugin development to create innovative tools for musicians and producers.
Tri‑Beat — Polyrhythm/Polymeter with Shapes
JUCE • C++ • Audio DSP • Realtime
A performance‑oriented metronome & groove designer using concentric polygons to create polyrhythms and polymeters. Accents, one‑shot samples, and a global 4/4 clock for alignment.
DDSP Sax Transformer
Python • PyTorch • DDSP • TorchScript/ONNX
A Differentiable Digital Signal Processing (DDSP) Autoencoder that transforms the timbre of any input sound into a tenor saxophone. The model is trained on tenor saxophone recordings and their extracted fundamental frequency (f0) tracks.
IR Extractor — Deconvolution Toolkit
JUCE • C++ • FFT • Convolution • Tooling
A desktop utility to derive impulse responses (IR) from dry/wet recordings using spectral division. Includes trim/normalize and export to WAV for convolution reverbs.
Music Genre Classification
TensorFlow • Keras • CNN & MFCC • Audio ML
A machine learning pipeline for automatic music genre recognition. Combines MFCC feature-based dense networks and a VGG-style CNN on Mel-spectrograms. Trained on the GTZAN dataset and supports prediction from any uploaded audio file.
DDSP Timbre Transfer
Python • PyTorch • DDSP • TorchScript/ONNX
This Project contains a Differentiable Digital Signal Processing (DDSP) model trained for timbre transformation at 48kHz.
The model enables users to input an audio signal (e.g., guitar, vocal, synth, etc.) and transform its timbre towards a target sound, while preserving the expressive dynamics and temporal structure of the original performance.
Shimmer Reverb
JUCE • C++ • ZITAREV • FAUST
A cinematic shimmer reverb using ZitaRev core + granular pitch-shift layers (octave, fifth, etc). This project contains a minimal, Generic-GUI Audio Plugin (VST3 + Standalone). Tested on Windows 10/11 + Visual Studio 2022.