Perceptual Metrics of Audio - perceptually relevant loss function. DPAM and CDPAM

Pytorch implementation of "A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences", Pranay Manocha et al. - unofficial work in progress

Speaker embedding (d-vector) trained with GE2E loss

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

Audio super resolution using neural networks

The Implementation of FastSpeech based on pytorch.

AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

A modified VITS that utilizes phoneme duration's ground truth for better robustness

This repository presents a subset of our proposed FSD dataset for song deepfake detection.

Curated list of python software and packages related to scientific research in audio

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis