In-context Text-to-Speech on Switchboard (SWBD)
0.608Similarity Score (Sim-o)AUDIOBOX SPEECH
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AUDIOBOX SPEECHTraining data=100K hours2023.12 | 0.608 | 9.1 | |
| VoiceboxTraining data=60K hours2023.12 | 0.477 | 10.6 | |
| YourTTSTraining data=600 hours2023.12 | 0.291 | 11.8 |