Single speaker neutral
| Prosody | Reference | GST | VAE | MIST Tacotron 10 | MIST Tacotron 1 |
|---|---|---|---|---|---|
| neutral 1 | |||||
| neutral 2 |
Single speaker emotion
| Emotion | Reference | GST | VAE | MIST Tacotron 10 | MIST Tacotron 1 |
|---|---|---|---|---|---|
| angry | |||||
| disgusting | |||||
| fear | |||||
| happy | |||||
| sad | |||||
| surprise |
multi speaker neutral
| Prosody | Reference | GST | VAE | MIST Tacotron |
|---|---|---|---|---|
| Woman1 | ||||
| Woman2 | ||||
| Woman3 | ||||
| Man1 | ||||
| Woman with Cheolla dialect | ||||
| Man2 |
multi speaker emotion
| Emotion | Reference | GST | VAE | MIST Tacotron |
|---|---|---|---|---|
| Angry 1 | ||||
| Angry 2 | ||||
| Happy 1 | ||||
| Happy 2 | ||||
| Sad 1 | ||||
| Sad 2 |
Non-linear prosody transfer
| Reference_sad | nea_happy | nea_sad | nee_sad | neo_neutral |
|---|---|---|---|---|