OSM-one-shot-multispeaker

End-2-end speech synthesis with recurrent neural networks

This repository contains PyTorch implementation of 4 different models for classification of emotions of the speech.

Linear Prediction Coefficients estimation from mel-spectrogram implemented in Python based on Levinson-Durbin algorithm.

Attention-based Hybrid CNN-LSTM and Spectral Data Augmentation for COVID-19 Diagnosis from Cough Sound

Open Source Implementation of Neural Voice Cloning with Few Audio Samples (Baidu Research)

Deep Multi-Speech model

Music genre classification using deep learning

The mel spectrogram generator using conditional WGAN-GP. For the mel spectrogram inverter, look up HiFi-GAN

Introduction to Digital Signal Processing for Machine Learning