PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
-
Updated
Aug 25, 2021 - Python
PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
This project enhances Text-to-Speech systems by integrating advanced emotion embeddings, allowing for more expressive and human-like speech synthesis. By capturing the nuances of human emotions, our approach aims to create synthetic voices that resonate with listeners, enabling effective emotional expression in speech generation.
Add a description, image, and links to the emotional-speech-synthesis topic page so that developers can more easily learn about it.
To associate your repository with the emotional-speech-synthesis topic, visit your repo's landing page and select "manage topics."