dongsig Goto Github PK

glow-tts

A Generative Flow for Text-to-Speech via Monotonic Alignment Search

gmm1d

A simple example of one-dimensional Gaussian mixture model

google-research

Google AI Research

hideandspeak

idrnd_antispoofing_solution

2nd place solution for ID R&D Voice Antispoofing Challenge

irapt

Instantaneous pitch estimation based on RAPT framework (EUSIPCO-2012)

iva4cocktail

Neural network density models for speech separation.

kaldi_rt_decoder

using microphone

kalmannet_tsp

code for KalmanNet

keras-serving

bring keras-models to production with tensorflow-serving and nodejs + docker :pizza:

kws

An End-to-End Architecture for Keyword Spotting and Voice Activity Detection

kws-1

Keyword Spotting for detecting a word in an audio file

kws-pytorch

A KWS model trained on SpeechCommands dataset, written in PyTorch.

liquid-dsp

digital signal processing library for software-defined radios

mcmil

A multiclass multiple instance learning method. Only need to know whether any instance of a class exists or not in a sample. Demonstration on multiple object detection and localization.

multi-task-speech-classification

Multi-Task Speech classification of accent and gender of an english speaker on Mozilla's common voice dataset

musegan

An AI for Music Generation

music-audio-tagging-at-scale-models

Tensorflow implementation of the models used in "End-to-end learning for music audio tagging at scale"

music-auto_tagging-keras

Music auto-tagging models and trained weights in keras/theano

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

nn-vad

simple dnn based vad

nnaec-neuralnetworkbasedacousticechocancellation

NNAEC-Neural Network based Acoustic Echo Cancellation

nnaudio

Audio processing by using pytorch 1D convolution network

open-speaker-verification

speaker verification tool

opus

Modern audio compression for the internet.

paddlespeech

Easy-to-use Speech Toolkit including SOTA ASR pipeline, influential TTS with text frontend and End-to-End Speech Simultaneous Translation.

panotti

A multi-channel neural network audio classifier using Keras

percepnet

(Under construct) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

percepnet-keras

percepnet implemented using Keras, still need to be optimized and tuned.

ppg-vc

PPG-Based Voice Conversion