voicerestore

A neural network for end-to-end speech denoising

Deep Recurrent Neural Networks for Source Separation

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

This repo contains the official PyTorch implementation of "Audio Super Resolution in the Spectral Domain" (ICASSP 2023)

Official pytorch implementation of the paper: "Catch-A-Waveform: Learning to Generate Audio from a Single Short Example" (NeurIPS 2021)

Source code for the paper titled "Speech Denoising without Clean Training Data: a Noise2Noise Approach". Paper accepted at the INTERSPEECH 2021 conference. This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples.

Unofficial implementation of ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech

The official PyTorch implementation of VM-ASR, a model designed for high-fidelity audio super-resolution.

Conditional Flow matching for Image and video