← all emotions
Distress
Best adapter: rank 16 , checkpoint seen 3336 · EmoNet-z +1.87 (baseline 0.518) · blend 0.64 · genu 0.239 · speaker-sim 0.299.
Instruction prompt: GENERAL: A voice that is adult; extremely carrying anguish; 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 -0.74 ±0.00 · bl 0.2 · gn 0.1 ▲ high -0.74
▼ low -0.74
z mean -0.74 ±0.00 · bl 0.3 · gn 0.1 ▲ high -0.74
▼ low -0.74
z mean -0.56 ±0.31 · bl 0.6 · gn 0.2 ▲ high +0.05
▼ low -0.74
with emo reference
z mean -0.74 ±0.00 · bl 0.3 · gn 0.3 ▲ high -0.74
▼ low -0.74
z mean -0.23 ±0.59 · bl 0.3 · gn 0.3 ▲ high +0.88
▼ low -0.74
z mean +0.57 ±0.82 · bl 0.5 · gn 0.4 ▲ high +1.99
▼ low -0.34
Sentence 2
no reference
z mean -0.74 ±0.00 · bl 0.7 · gn 0.1 ▲ high -0.74
▼ low -0.74
z mean -0.74 ±0.00 · bl 0.5 · gn 0.1 ▲ high -0.74
▼ low -0.74
z mean -0.71 ±0.05 · bl 0.7 · gn 0.2 ▲ high -0.61
▼ low -0.74
with emo reference
z mean -0.66 ±0.16 · bl 0.4 · gn 0.4 ▲ high -0.33
▼ low -0.74
z mean -0.74 ±0.00 · bl 0.1 · gn 0.2 ▲ high -0.74
▼ low -0.74
z mean -0.37 ±0.45 · bl 0.5 · gn 0.4 ▲ high +0.25
▼ low -0.74
Sentence 3
no reference
z mean -0.11 ±0.48 · bl 0.2 · gn 0.1 ▲ high +0.47
▼ low -0.74
z mean -0.28 ±0.33 · bl 0.4 · gn 0.1 ▲ high +0.25
▼ low -0.74
z mean +0.03 ±0.38 · bl 0.6 · gn 0.2 ▲ high +0.46
▼ low -0.68
with emo reference
z mean -0.52 ±0.31 · bl 0.1 · gn 0.3 ▲ high +0.04
▼ low -0.74
z mean +0.45 ±0.78 · bl 0.2 · gn 0.3 ▲ high +1.41
▼ low -0.74
z mean -0.41 ±0.27 · bl 0.6 · gn 0.4 ▲ high -0.19
▼ low -0.74
Sentence 4
no reference
z mean -0.74 ±0.00 · bl 0.2 · gn 0.1 ▲ high -0.74
▼ low -0.74
z mean -0.74 ±0.00 · bl 0.4 · gn 0.1 ▲ high -0.74
▼ low -0.74
z mean -0.74 ±0.00 · bl 0.6 · gn 0.3 ▲ high -0.74
▼ low -0.74
with emo reference
z mean -0.74 ±0.00 · bl 0.3 · gn 0.3 ▲ high -0.74
▼ low -0.74
z mean +0.57 ±0.54 · bl 0.3 · gn 0.3 ▲ high +1.59
▼ low -0.03
z mean -0.36 ±0.75 · bl 0.3 · gn 0.4 ▲ high +1.14
▼ low -0.74
Sentence 5
no reference
z mean -0.74 ±0.00 · bl 0.2 · gn 0.1 ▲ high -0.74
▼ low -0.74
z mean -0.74 ±0.00 · bl 0.5 · gn 0.1 ▲ high -0.74
▼ low -0.74
z mean -0.74 ±0.00 · bl 0.4 · gn 0.2 ▲ high -0.74
▼ low -0.74
with emo reference
z mean -0.74 ±0.00 · bl 0.2 · gn 0.3 ▲ high -0.74
▼ low -0.74
z mean -0.16 ±0.52 · bl 0.3 · gn 0.4 ▲ high +0.60
▼ low -0.74
z mean +0.33 ±0.95 · bl 0.5 · gn 0.4 ▲ high +1.46
▼ low -0.74