ishine's Projects
tacotron for research on Chinese speech synthesis and Taiwanese speech synthesis from Chinese input text sequence with different granularities
DeepMind's Tacotron-2 Tensorflow implementation
tacotron-2(tensorflow) + melgan(pytorch) chinese TTS
A Tacotron implementation with location relative attention
Tacotron text to speech in C++(synthesize only)
Tacotron, Korean, Wavenet-Vocoder, Korean TTS
Forked from https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/Tacotron2 and merged with https://github.com/Rayhane-mamah/Tacotron-2
Tacotron 2 - PyTorch implementation with faster-than-realtime inference
Implementation of TTS with combination of Tacotron2 and HiFi-GAN
PyTorch reimplementation of Tacotron2 in Mandarin
Tacotron2 model from Nvidia, adapted to take as input 40-phoneme PPGs as input, instead of the usual character embeddings.
Implementation of "Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis"
pretrain tacotron2 decoder
Train tacotron on a mandarin dataset
Multi-Speaker Tacotron2 with VAE
δΈδΈͺθ½»ιηΊ§ηε₯εζ 注ε°ε·₯ε
·
Code for the Paper Speech Recognition and Multi-Speaker Diarization of Long Conversations
Code for Talk-to-Edit (ICCV2021). Paper: Talk-to-Edit: Fine-Grained Facial Editing via Dialog.
Demo programs for the Talking Head Anime from a Single Image 2: More Expressive project.
MSc Dissertation
talking_head_anime
TalkNet: Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection
Source code of paper "Incorporating prior knowledge into word embedding for Chinese word similarity measurement", accepted by ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP).
Task-oriented dialog system toolkits