← all emotions
Intoxication Altered States of Consciousness
Best adapter: rank 32 , checkpoint seen 1672 · EmoNet-z +1.15 (baseline -0.436) · blend 0.713 · genu 0.196 · speaker-sim 0.441.
Instruction prompt: GENERAL: A voice that is genuine in delivery.
SCRIPT:
Five neutral sentences, each in English / Deutsch / Français, no reference vs with emotion reference (a same-emotion training clip supplies the voice; the prompt applies the emotion).
Each cell = 5 seeds. We show mean±std of the emotion score and play the highest and lowest seed (top = strongest emotion, bottom = weakest), since a fixed seed pins the sampling and single clips vary.
Sentence 1
no reference
z mean +0.03 ±0.53 · bl 0.2 · gn 0.1 ▲ high +0.85
▼ low -0.49
z mean +0.20 ±1.29 · bl 0.3 · gn 0.1 ▲ high +2.79
▼ low -0.50
z mean -0.00 ±0.72 · bl 0.5 · gn 0.2 ▲ high +1.43
▼ low -0.48
with emo reference
z mean -0.46 ±0.02 · bl 0.1 · gn 0.4 ▲ high -0.43
▼ low -0.48
z mean -0.34 ±0.23 · bl 0.0 · gn 0.1 ▲ high +0.12
▼ low -0.47
z mean -0.46 ±0.01 · bl 0.2 · gn 0.2 ▲ high -0.44
▼ low -0.48
Sentence 2
no reference
z mean -0.44 ±0.08 · bl 0.5 · gn 0.1 ▲ high -0.29
▼ low -0.51
z mean +0.48 ±1.22 · bl 0.3 · gn 0.1 ▲ high +2.82
▼ low -0.49
z mean +0.31 ±1.24 · bl 0.5 · gn 0.2 ▲ high +2.78
▼ low -0.49
with emo reference
z mean -0.44 ±0.02 · bl 0.5 · gn 0.3 ▲ high -0.41
▼ low -0.47
z mean +0.89 ±1.68 · bl 0.1 · gn 0.2 ▲ high +3.36
▼ low -0.47
z mean -0.19 ±0.55 · bl 0.5 · gn 0.4 ▲ high +0.91
▼ low -0.47
Sentence 3
no reference
z mean -0.42 ±0.08 · bl 0.2 · gn 0.1 ▲ high -0.26
▼ low -0.49
z mean +0.77 ±1.51 · bl 0.4 · gn 0.1 ▲ high +2.97
▼ low -0.47
z mean -0.31 ±0.29 · bl 0.4 · gn 0.1 ▲ high +0.26
▼ low -0.49
with emo reference
z mean -0.46 ±0.01 · bl 0.0 · gn 0.3 ▲ high -0.44
▼ low -0.47
z mean +1.87 ±1.68 · bl 0.2 · gn 0.1 ▲ high +4.00
▼ low -0.44
z mean -0.43 ±0.01 · bl 0.3 · gn 0.4 ▲ high -0.42
▼ low -0.46
Sentence 4
no reference
z mean -0.27 ±0.41 · bl 0.1 · gn 0.1 ▲ high +0.55
▼ low -0.50
z mean +0.33 ±0.80 · bl 0.3 · gn 0.1 ▲ high +1.35
▼ low -0.50
z mean +0.86 ±1.08 · bl 0.4 · gn 0.2 ▲ high +2.29
▼ low -0.14
with emo reference
z mean -0.46 ±0.02 · bl 0.1 · gn 0.2 ▲ high -0.43
▼ low -0.48
z mean -0.02 ±0.61 · bl 0.1 · gn 0.2 ▲ high +1.14
▼ low -0.45
z mean -0.43 ±0.08 · bl 0.3 · gn 0.4 ▲ high -0.27
▼ low -0.50
Sentence 5
no reference
z mean +1.49 ±1.72 · bl 0.3 · gn 0.2 ▲ high +3.70
▼ low -0.48
z mean +0.26 ±0.65 · bl 0.3 · gn 0.1 ▲ high +1.14
▼ low -0.48
z mean +0.10 ±1.12 · bl 0.3 · gn 0.2 ▲ high +2.34
▼ low -0.48
with emo reference
z mean -0.44 ±0.01 · bl 0.2 · gn 0.2 ▲ high -0.43
▼ low -0.46
z mean +0.39 ±1.02 · bl 0.1 · gn 0.1 ▲ high +1.74
▼ low -0.50
z mean -0.29 ±0.34 · bl 0.1 · gn 0.2 ▲ high +0.39
▼ low -0.50