# 一. 语音合成(文本转语音)
title:High Fidelity Speech Synthesis with Adversarial Networks
link:https://openreview.net/pdf?id=r1gfQgSFDr
code:https://github.com/mbinkowski/DeepSpeechDistances
# 二. 语音识别(语音转文本)
- https://blog.csdn.net/chengyq116/article/details/106577887 https://github.com/gentaiscool/end2end-asr-pytorch
- https://blog.csdn.net/chinatelecom08/article/details/85051817
- https://blog.csdn.net/chinatelecom08/article/details/85013535?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.edu_weight&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.edu_weight
- https://blog.csdn.net/sunshuai_coder/article/details/83658625?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.edu_weight&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.edu_weight
- https://mp.weixin.qq.com/s/cAGzqV5zLYEBbRpuIGj3zw
- https://mp.weixin.qq.com/s/_7wNg1ofO351NHEuAgxVIg
# 三. 深度学习语音分离
# 四.超全nlp