bryceirvin

bryceirvin's Stars

• CorentinJ/Real-Time-Voice-Cloning

  Clone a voice in 5 seconds to generate arbitrary speech in real-time

  Language:Python52k9371.1k8.7k

• google-research/google-research

  Google Research

  Language:Jupyter Notebook33.8k7511.2k7.8k

• xiph/rnnoise

  Recurrent neural network for audio noise reduction

  Language:C4k150197890

• readbeyond/aeneas

  aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

  Language:Python2.5k73209222

• keunwoochoi/kapre

  kapre: Keras Audio Preprocessors

  Language:Python9182397146

• liusongxiang/ppg-vc

  PPG-Based Voice Conversion

  Language:Python325103172

• YuanGongND/gopt

  Code for the ICASSP 2022 paper "Transformer-Based Multi-Aspect Multi-Granularity Non-native English Speaker Pronunciation Assessment".

  Language:Python14253525

• RF5/simple-speaker-embedding

  A speaker embedding network in Pytorch that is very quick to set up and use for whatever purposes.

  Language:Jupyter Notebook822611

• nkrao220/accent-classification

  Accent Classification in Speech

  Language:Python24115

• acetylSv/non-parallel-rhythm-flexible-VC

  PyTorch implementation of: Rhythm-Flexible Voice Conversion without Parallel Data Using Cycle-GAN over Phoneme Posteriorgram Sequences

  Language:Python11420

• zuhairmhtb/AudioClassification

  This software is a demonstration of Audio Signal Processing and Machine Learning using Python and Tensorflow. The software contains a GUI that can stream audio via webcams or external audio devices connected to the computer and process the audio in real time using a Convolutional and/or a Recurrent Neural Network in order to perform audio classification like speech recognition, music classification, etc. (Depending on how the network was trained). The data set can be arranged in directories where the name of a parent directory represents a classification class. In this way a single network can be trained for multiple types of binary independent audio data eventually building a complex neural network.

  Language:Python9201

• segerpeter07/QEA-Sound-Reproduction

  Attempting to create a voice identification system using eigen-based linear algebra and also create a voice synthesis system using a Hidden Markov Model (HMM) and Mel Log Spectrum Approximation Filtering.

  Language:CSS10