0. Contents
1. Primary Emotion Synthesis
This test is mainly used to verify the ability of the fine-tuned model to synthesize primary emotions and the effectiveness of the introduced fine-grained annotations in improving the model's performance.
1.1 Angry
| ID | Speaker | GT | GT(voc.) | EmoDiff | EmoMix | Ours | Ours w/o FGR |
|---|---|---|---|---|---|---|---|
| 001 | 0013 | ||||||
| 0015 | |||||||
| 002 | 0013 | ||||||
| 0015 | |||||||
| 003 | 0013 | ||||||
| 0015 | |||||||
| 004 | 0013 | ||||||
| 0015 | |||||||
| 005 | 0013 | ||||||
| 0015 |
1.2 Happy
| ID | Speaker | GT | GT(voc.) | EmoDiff | EmoMix | Ours | Ours w/o FGR |
|---|---|---|---|---|---|---|---|
| 001 | 0013 | ||||||
| 0015 | |||||||
| 002 | 0013 | ||||||
| 0015 | |||||||
| 003 | 0013 | ||||||
| 0015 | |||||||
| 004 | 0013 | ||||||
| 0015 | |||||||
| 005 | 0013 | ||||||
| 0015 |
1.3 Neutral
| ID | Speaker | GT | GT(voc.) | EmoDiff | EmoMix | Ours | Ours w/o FGR |
|---|---|---|---|---|---|---|---|
| 001 | 0013 | ||||||
| 0015 | |||||||
| 002 | 0013 | ||||||
| 0015 | |||||||
| 003 | 0013 | ||||||
| 0015 | |||||||
| 004 | 0013 | ||||||
| 0015 | |||||||
| 005 | 0013 | ||||||
| 0015 |
1.4 Sad
| ID | Speaker | GT | GT(voc.) | EmoDiff | EmoMix | Ours | Ours w/o FGR |
|---|---|---|---|---|---|---|---|
| 001 | 0013 | ||||||
| 0015 | |||||||
| 002 | 0013 | ||||||
| 0015 | |||||||
| 003 | 0013 | ||||||
| 0015 | |||||||
| 004 | 0013 | ||||||
| 0015 | |||||||
| 005 | 0013 | ||||||
| 0015 |
1.5 Surprise
| ID | Speaker | GT | GT(voc.) | EmoDiff | EmoMix | Ours | Ours w/o FGR |
|---|---|---|---|---|---|---|---|
| 001 | 0013 | ||||||
| 0015 | |||||||
| 002 | 0013 | ||||||
| 0015 | |||||||
| 003 | 0013 | ||||||
| 0015 | |||||||
| 004 | 0013 | ||||||
| 0015 | |||||||
| 005 | 0013 | ||||||
| 0015 |
2. Mixed-emotion Synthesis
Mixed-emotion samples.
2.1 Surprise with Angry
| ID | Speaker | Configure | Ours | Emomix |
|---|---|---|---|---|
| 001 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 002 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 003 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 004 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 005 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% |
2.2 Surprise with Happy
| ID | Speaker | Configure | Ours | Emomix |
|---|---|---|---|---|
| 001 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 002 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 003 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 004 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 005 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% |
2.3 Surprise with Sad
| ID | Speaker | Configure | Ours | Emomix |
|---|---|---|---|---|
| 001 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 002 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 003 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 004 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 005 | 0013 | 20%, 80% | ||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% | ||||
| 0015 | 20%, 80% | |||
| 40%, 60% | ||||
| 60%, 40% | ||||
| 80%, 20% |