Stars
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-t…
Command line tool for displaying and adding C2PA manifests
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
Convmelspec: Convertible Melspectrograms via 1D Convolutions
FxNorm-Automix - Implementation of automatic music mixing systems. We show how we can use wet music data and repurpose it to train a fully automatic mixing system
Official repo of ICASSP 2022 paper - Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization
Control adaptive filters with neural networks.
DeepAFx-ST - Style transfer of audio effects with differentiable signal processing. Please see https://csteinmetz1.github.io/DeepAFx-ST/
Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".
Third-party audio effects plugins as differentiable layers within deep neural networks.
Code for paper: "Deep Embeddings and Section Fusion Improve Music Segmentation"
Who calls the shots? Rethinking Few-Shot Learning for Audio (WASPAA 2021)
Train custom adaptive filter optimizers without hand tuning or extra labels.
Pitch-shifting, time-stretching, and vocoding of speech with Controllable LPCNet (CLPCNet)
Perceptual Metrics of Audio - perceptually relevant loss function. DPAM and CDPAM