Speech Synthesis On North American English
Métriques
Mean Opinion Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Mean Opinion Score |
|---|---|
| wavenet-a-generative-model-for-raw-audio | 3.67 |
| merging-k-means-with-hierarchical-clustering | 0 |
| wavenet-a-generative-model-for-raw-audio | 4.21 |
| natural-tts-synthesis-by-conditioning-wavenet | 4.526 |
| tacotron-towards-end-to-end-speech-synthesis | 4.001 |
| natural-tts-synthesis-by-conditioning-wavenet | 4.341 |
| wavenet-a-generative-model-for-raw-audio | 3.86 |