No description
80f95b8db7
Replace placeholder stub with a complete additive synthesiser: - 64 harmonics, 5 parameter groups (Spectral Shape, Temporal, Phase, Modulation, Master), 48 NISPS-mapped params in exact spec order - Spectral descriptors: per-harmonic amplitudes, tilt, inharmonicity, odd/even balance, formant Gaussian shaping - Temporal: dual ADSR (global + brightness), spectral flux LFO - Phase: randomisation, walk, inter-partial beating, stereo spread, noise floor with colour, sub-harmonic - Modulation: vibrato (delayed onset), tremolo, harmonic drift, formant resonance peaks - Master: level, vel coupling, portamento, saturation waveshaper, fine-tune cents - additive-processor.js: AudioWorklet processor extending FaustWorkletProcessor with dynamic zone-table construction at init, _onNoteOn/Off, _renderBlock, _onSetParam - additive.json: Faust descriptor with 48 params in spec-ordered groups (numeric prefixes force alphabetical sort = spec order) - additive.wasm: compiled with faust 2.83.1 -lang wasm -cn additive |
||
|---|---|---|
| .beads | ||
| .claude/worktrees/agent-ae87fe47/playground/js/shapeseq | ||
| .github/workflows | ||
| .vscode | ||
| data | ||
| modes | ||
| nisps-core | ||
| playground | ||
| src | ||
| tests/e2e | ||
| vcv | ||
| voicespaces | ||
| .gitignore | ||
| .gitmodules | ||
| AGENTS.md | ||
| ChannelStripAudioApp.hpp | ||
| CLAUDE.md | ||
| IMLInterface.hpp | ||
| LICENSE | ||
| MEMLNaut-NISPS.ino | ||
| NISPS_CORE_EXTRACTION_PLAN.md | ||
| NISPS_CORE_TASKS.md | ||
| package.json | ||
| PAFSynthAudioApp.hpp | ||
| playwright.config.js | ||
| README.md | ||
| ThruAudioApp.hpp | ||
| XiasriAnalysis.cpp | ||
| XiasriAnalysis.hpp | ||
| XIASRIAudioApp.hpp | ||
Neural Interactive Shaping of Parameter Spaces
https://musicallyembodiedml.github.io/memlnaut/approaches/nisps
Web Playground
Try NISPS in your browser — no hardware required:
cd playground
python3 -m http.server
# Open http://localhost:8000
Train a neural network to map joystick positions to generative visuals through interactive machine learning. Two learning modes: direct example mapping and reinforcement learning with thumbs up/down feedback.
The playground UI includes an Expand toggle on the visual surface so you can make the canvas nearly full-screen while compressing parameter/control panels into a minimal strip beneath it.