| license: cc-by-nc-sa-4.0 | |
| language: | |
| - en | |
| pipeline_tag: text-to-speech | |
| tags: | |
| - msp-podcast | |
| - emotion-recognition | |
| - audio | |
| - speech | |
| - styletts2 | |
| - mimic3 | |
| - speech-emotion-recognition | |
| - dkounadis | |
| # Artificial StyleTTS2 | |
| Using Mimic-3 Synthetic Speech to Drive StyleTTS2 | |
| **[arXiv Coming soon]()** | |
| ``` | |
| ``` | |
| See demo at [SHIFT TTS tool](https://github.com/audeering/shift/tree/main) | |