MelissaChen15

control-vc

This is the implementation for "ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Rhythm"

asgan

Training code and trained checkpoints for ASGAN.

ASVSpoof2021

ASVspoof 2021 Baseline Systems

AudioLDM

AudioLDM: Generate speech, sound effects, music and beyond, with text.

ayu-Terminal-app

ayu color themes for Terminal.app

carganVC

Official repository for the paper "Chunked Autoregressive GAN for Conditional Waveform Synthesis"

CSC446-Machine-Learning

ddsp_pytorch

Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch

dtaidistance

Time series distances: Dynamic Time Warping (DTW)

espnet_model_zoo

ESPnet Model Zoo

FastDiff

FeelingPlus

This repo is for FeelingPlus(previously MagicStory) project, AR/VR Ph.D. Training Program Capstone Course 2022, University of Rochester.

gan-feats-4spoof

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

gitignore

A collection of useful .gitignore templates

gradio_tagpage

Create UIs for your machine learning model in Python in 3 minutes

jiant

The jiant toolkit for general-purpose text understanding models

leaf-audio

links_clustering

Implementation of the Links Online Clustering algorithm: https://arxiv.org/abs/1801.10123

melissachen15.github.io

personal blog of dotdot

openTSNE

Extensible, parallel implementations of t-SNE

pgmpy

Python Library for Probabilistic Graphical Models

ProDiff

PyTorch Implementation of ProDiff (ACM-MM'22) with a Extremely-Fast diffusion speech synthesis pipeline

quant

scikit-feature

open-source feature selection repository in python (DMML Lab@ASU)

speech-emotion-recognition

speech emotion recognition using a convolutional recurrent networks based on IEMOCAP

synthesis_evaluation

Evaluation metrics for voice conversion, text-to-speech and other audio synthesis tasks.

textual_inversion

time-series-forcasting

Using K-NN, SVM, Bayes, LSTM, and multi-variable LSTM models on time series forecasting

VPC2022_UR

Baseline Recipe for VoicePrivacy Challenge 2022: anonymization systems and evaluation software

WaveRNN

WaveRNN Vocoder + TTS