← all emotions
Sourness
Best adapter: rank 16 , checkpoint seen 1672 · EmoNet-z -0.65 (baseline -0.649) · blend 0.574 · genu 0.153 · speaker-sim 0.097.
Instruction prompt: GENERAL: A voice that is adult; extremely carrying acerbity; 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 -0.65 ±0.00 · bl 0.2 · gn 0.1 ▲ high -0.64
▼ low -0.65
z mean -0.11 ±0.44 · bl 0.3 · gn 0.1 ▲ high +0.33
▼ low -0.64
z mean -0.61 ±0.08 · bl 0.5 · gn 0.1 ▲ high -0.46
▼ low -0.66
with emo reference
z mean -0.65 ±0.00 · bl 0.2 · gn 0.1 ▲ high -0.64
▼ low -0.65
z mean +1.42 ±0.29 · bl 0.1 · gn 0.1 ▲ high +1.69
▼ low +0.94
z mean -0.45 ±0.28 · bl 0.2 · gn 0.2 ▲ high +0.07
▼ low -0.65
Sentence 2
no reference
z mean -0.64 ±0.01 · bl 0.6 · gn 0.1 ▲ high -0.61
▼ low -0.64
z mean -0.32 ±0.50 · bl 0.3 · gn 0.1 ▲ high +0.65
▼ low -0.65
z mean -0.63 ±0.02 · bl 0.6 · gn 0.2 ▲ high -0.58
▼ low -0.65
with emo reference
z mean -0.55 ±0.15 · bl 0.6 · gn 0.1 ▲ high -0.26
▼ low -0.65
z mean +0.20 ±0.59 · bl 0.1 · gn 0.1 ▲ high +0.91
▼ low -0.65
z mean -0.53 ±0.22 · bl 0.3 · gn 0.2 ▲ high -0.09
▼ low -0.65
Sentence 3
no reference
z mean -0.64 ±0.00 · bl 0.1 · gn 0.1 ▲ high -0.64
▼ low -0.65
z mean -0.65 ±0.01 · bl 0.4 · gn 0.1 ▲ high -0.64
▼ low -0.66
z mean -0.46 ±0.27 · bl 0.5 · gn 0.2 ▲ high +0.05
▼ low -0.66
with emo reference
z mean -0.65 ±0.00 · bl 0.3 · gn 0.1 ▲ high -0.65
▼ low -0.66
z mean -0.04 ±0.63 · bl 0.1 · gn 0.1 ▲ high +0.96
▼ low -0.65
z mean -0.23 ±0.56 · bl 0.3 · gn 0.1 ▲ high +0.87
▼ low -0.65
Sentence 4
no reference
z mean -0.65 ±0.00 · bl 0.1 · gn 0.1 ▲ high -0.64
▼ low -0.65
z mean -0.65 ±0.00 · bl 0.3 · gn 0.1 ▲ high -0.64
▼ low -0.65
z mean -0.23 ±0.45 · bl 0.4 · gn 0.2 ▲ high +0.34
▼ low -0.65
with emo reference
z mean -0.47 ±0.36 · bl 0.2 · gn 0.1 ▲ high +0.25
▼ low -0.65
z mean -0.42 ±0.47 · bl 0.1 · gn 0.1 ▲ high +0.52
▼ low -0.66
z mean -0.15 ±0.57 · bl 0.2 · gn 0.2 ▲ high +0.65
▼ low -0.65
Sentence 5
no reference
z mean -0.65 ±0.00 · bl 0.1 · gn 0.1 ▲ high -0.64
▼ low -0.65
z mean -0.36 ±0.50 · bl 0.4 · gn 0.2 ▲ high +0.63
▼ low -0.65
z mean -0.64 ±0.02 · bl 0.4 · gn 0.1 ▲ high -0.59
▼ low -0.66
with emo reference
z mean -0.64 ±0.00 · bl 0.2 · gn 0.1 ▲ high -0.64
▼ low -0.65
z mean -0.58 ±0.07 · bl 0.1 · gn 0.2 ▲ high -0.47
▼ low -0.66
z mean -0.41 ±0.47 · bl 0.2 · gn 0.1 ▲ high +0.52
▼ low -0.65