xiangyang's repositories
FFmpeg
Mirror of git://source.ffmpeg.org/ffmpeg.git
py-webrtcvad
Python interface to the WebRTC Voice Activity Detector
tacotron2
Tacotron 2 - PyTorch implementation with faster-than-realtime inference
WaveRNN
WaveRNN Vocoder + TTS
CrossLingualDepParser
Zero-Shot Cross-Lingual Transfer with Order Differences
Emotional-TTS
Korean Emotional End-to-End Neural Speech synthesizer, ML4audio, NIPS2017
TTS
Deep learning for Text to Speech
tacotron2-vae
Implementation of "Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis"
gantts
PyTorch implementation of GAN-based text-to-speech synthesis and voice conversion (VC)
style-token_tacotron2
style token with tacotron2
GAN-Voice-Conversion
Implementation of GAN architectures for Voice Conversion
Tacotron2-Wavenet-Korean-TTS
Korean TTS, Tacotron2, Wavenet
State_of_the_art_tacotron2_model_reproduction
My Master Research Project on NLP
SeqGAN
Implementation of Sequence Generative Adversarial Nets with Policy Gradient
VAD
Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.
vae_tacotron2
VAE Tacotron 2, an alternative of GST Tacotron
merlin
This is now the official location of the Merlin project.
StarGAN-Voice-Conversion
full tensorflow implementation of the paper: StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks https://arxiv.org/abs/1806.02169
unsup-cross-lingual-embedding-transfer
Code for "Unsupervised Cross-lingual Transfer of Word Embedding Spaces" in EMNLP 2018
SWConvertVideoToAudio
Python批量转换 视频 为 音频MP3（即提取音频文件）
Voice-Conversion-1
Voice Conversion from non-parallel data with VAE-GAN