adrianbarahona/noisebandnet
Code for the "NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks" paper.
This tool helps sound designers, game developers, or audio researchers create new, complex sound effects from existing audio samples. You provide a collection of sound files or a single audio recording, and it generates novel, controllable sound variations based on features like loudness or user-drawn control curves. The output is a new synthetic sound effect that retains characteristics of the original but can be manipulated in real-time.
No commits in the last 6 months.
Use this if you need to generate a diverse range of unique sound effects, such as impacts, whooshes, or atmospheric textures, with precise control over their sonic characteristics without recording them from scratch.
Not ideal if you're looking for simple pitch or tempo adjustments to existing musical recordings or speech, as it's designed for synthesis and manipulation of more abstract sound effects.
Stars
39
Forks
3
Language
Python
License
AGPL-3.0
Category
Last pushed
Jul 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/adrianbarahona/noisebandnet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.