Neural Voice Cloning in Deep Learning
Zhiqi Zhang
An research bringing the power of deep learning, innovation and future prospects together
Would you like to make your favorite film character to say different scripts, or speak like Barack Obama? This project will do that for you. The aim of this project is to research and study neural voice cloning models in deep learning which can clone the voice with only few seconds of input audio samples and the given text input. The project has studied the open-sourced model on GitHub by CorentinJ, which was inspired by a text-to-speech (TTS) synthesis system from Google.
Page Views:
The aim of this project is to research and study neural voice cloning models in deep learning which can clone the voice with only few seconds of input audio samples and the given text input. The project has studied the open-sourced model on GitHub by CorentinJ, which was inspired by a text-to-speech (TTS) synthesis system from Google ( Y. Jia et al., ‘Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis’).
