Veleslavia / conditioned-u-netLinks
Conditioned U-Net for Music Source Separation
☆20Updated 4 years ago
Alternatives and similar repositories for conditioned-u-net
Users that are interested in conditioned-u-net are comparing it to the libraries listed below
Sorting:
- ☆84Updated 2 years ago
- NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling☆37Updated 4 years ago
- UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation☆75Updated 3 years ago
- spectrogram inversion tools in PyTorch. Documentation: https://spectrogram-inversion.readthedocs.io☆51Updated 2 months ago
- PyTorch Dataset for Speech and Music audio☆77Updated last year
- This repo contains the source code of the first deep learning-base singing voice beat tracking system. It leverages WavLM and DistilHuBER…☆33Updated 2 years ago
- An unofficial implementation of Vector Quantization Voice Conversion (VQVC).☆29Updated 4 years ago
- Unsupervised Representation Learning for Singing Voice Separation☆22Updated 2 years ago
- [SpeechCom Journal] Learning and controlling the source-filter representation of speech with a variational autoencoder☆44Updated 2 years ago
- A PyTorch implementation of the paper: "LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation" (ICAS…☆86Updated 2 years ago
- Who calls the shots? Rethinking Few-Shot Learning for Audio (WASPAA 2021)☆43Updated 3 years ago
- Implementation for "Music Enhancement via Image Translation and Vocoding"☆54Updated 3 years ago
- ☆32Updated 4 years ago
- This is an unofficial implementation of universal melgan according to https://arxiv.org/abs/2011.09631☆23Updated 2 years ago
- Quasi-Periodic Parallel WaveGAN Pytorch implementation☆46Updated 2 years ago
- ☆40Updated 5 years ago
- Phoneme Level Lyrics Alignment and Text-Informed Singing Voice Separation☆23Updated 3 years ago
- Official implementation of DualCycleGAN for nonparallel audio super resolution☆53Updated 2 years ago
- An invertible and differentiable implementation of the Constant-Q Transform (CQT).☆62Updated 2 years ago
- Training code and trained checkpoints for ASGAN.☆62Updated last year
- Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing☆70Updated 2 years ago
- This repo contains code for comparing audio representation sin the task of audio synthesis wth Generative Adversarial Networks (GAN)☆37Updated 2 years ago
- This repository contains laughter-related synthesis systems.☆13Updated 4 years ago
- This repository is the offical implementation for the paper 《Frequency-Temporal Attention Network for Singing Melody Extraction》.☆40Updated 2 years ago
- Self-supervised VQ-VAE for One-Shot Music Style Transfer☆97Updated 5 months ago
- Upsampling Artifacts in Neural Audio Synthesis – https://arxiv.org/abs/2010.14356☆79Updated 4 years ago
- A unified model for zero-shot singing voice conversion and synthesis☆22Updated 2 years ago
- An evaluation toolkit for voice conversion models.☆42Updated 4 years ago
- ☆64Updated 3 years ago
- Official repository of the paper "Solving Audio Inverse Problems with a Diffusion Model", submitted to ICASSP 23☆117Updated 2 years ago