← all emotions
Shame
Best adapter: rank 64 , checkpoint seen 1672 · EmoNet-z -0.09 (baseline -0.589) · blend 0.777 · genu 0.183 · speaker-sim 0.392.
Instruction prompt: GENERAL: A voice that is adult, with extremely carrying contrition and 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 -0.63 ±0.01 · bl 0.2 · gn 0.2 ▲ high -0.61
▼ low -0.63
z mean -0.62 ±0.00 · bl 0.4 · gn 0.1 ▲ high -0.61
▼ low -0.62
z mean -0.62 ±0.01 · bl 0.5 · gn 0.1 ▲ high -0.61
▼ low -0.63
with emo reference
z mean -0.63 ±0.00 · bl 0.1 · gn 0.1 ▲ high -0.63
▼ low -0.63
z mean -0.59 ±0.07 · bl 0.1 · gn 0.1 ▲ high -0.45
▼ low -0.63
z mean -0.62 ±0.01 · bl 0.3 · gn 0.1 ▲ high -0.61
▼ low -0.63
Sentence 2
no reference
z mean -0.21 ±0.84 · bl 0.6 · gn 0.2 ▲ high +1.46
▼ low -0.64
z mean -0.63 ±0.00 · bl 0.6 · gn 0.1 ▲ high -0.62
▼ low -0.63
z mean -0.62 ±0.01 · bl 0.7 · gn 0.2 ▲ high -0.61
▼ low -0.63
with emo reference
z mean -0.63 ±0.00 · bl 0.6 · gn 0.2 ▲ high -0.63
▼ low -0.64
z mean -0.63 ±0.01 · bl 0.1 · gn 0.1 ▲ high -0.62
▼ low -0.63
z mean -0.63 ±0.00 · bl 0.2 · gn 0.2 ▲ high -0.63
▼ low -0.63
Sentence 3
no reference
z mean -0.63 ±0.00 · bl 0.1 · gn 0.2 ▲ high -0.63
▼ low -0.64
z mean -0.53 ±0.17 · bl 0.3 · gn 0.1 ▲ high -0.19
▼ low -0.62
z mean -0.32 ±0.61 · bl 0.6 · gn 0.2 ▲ high +0.90
▼ low -0.63
with emo reference
z mean -0.63 ±0.00 · bl 0.2 · gn 0.0 ▲ high -0.63
▼ low -0.64
z mean -0.42 ±0.39 · bl 0.0 · gn 0.1 ▲ high +0.36
▼ low -0.62
z mean -0.63 ±0.01 · bl 0.2 · gn 0.2 ▲ high -0.63
▼ low -0.65
Sentence 4
no reference
z mean -0.63 ±0.01 · bl 0.2 · gn 0.2 ▲ high -0.62
▼ low -0.63
z mean -0.62 ±0.01 · bl 0.4 · gn 0.1 ▲ high -0.62
▼ low -0.63
z mean -0.62 ±0.00 · bl 0.4 · gn 0.2 ▲ high -0.62
▼ low -0.63
with emo reference
z mean -0.63 ±0.00 · bl 0.2 · gn 0.1 ▲ high -0.63
▼ low -0.64
z mean -0.62 ±0.01 · bl 0.0 · gn 0.1 ▲ high -0.61
▼ low -0.63
z mean -0.63 ±0.00 · bl 0.1 · gn 0.4 ▲ high -0.63
▼ low -0.64
Sentence 5
no reference
z mean -0.62 ±0.01 · bl 0.2 · gn 0.0 ▲ high -0.61
▼ low -0.63
z mean -0.62 ±0.00 · bl 0.6 · gn 0.1 ▲ high -0.62
▼ low -0.63
z mean -0.62 ±0.00 · bl 0.5 · gn 0.2 ▲ high -0.62
▼ low -0.63
with emo reference
z mean -0.63 ±0.00 · bl 0.2 · gn 0.0 ▲ high -0.63
▼ low -0.63
z mean -0.63 ±0.01 · bl 0.1 · gn 0.1 ▲ high -0.62
▼ low -0.63
z mean -0.63 ±0.00 · bl 0.0 · gn 0.1 ▲ high -0.63
▼ low -0.63