← all emotions
Concentration
Best adapter: rank 64 , checkpoint seen 3336 · EmoNet-z -0.40 (baseline -0.302) · blend 0.581 · genu 0.193 · speaker-sim 0.215.
Instruction prompt: GENERAL: A voice that is adult, with extremely carrying attention 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 -0.96 ±0.00 · bl 0.3 · gn 0.1 ▲ high -0.96
▼ low -0.96
z mean -0.91 ±0.10 · bl 0.4 · gn 0.1 ▲ high -0.71
▼ low -0.96
z mean -0.60 ±0.73 · bl 0.6 · gn 0.1 ▲ high +0.86
▼ low -0.96
with emo reference
z mean +0.22 ±0.61 · bl 0.4 · gn 0.3 ▲ high +0.75
▼ low -0.77
z mean +0.21 ±0.97 · bl 0.5 · gn 0.1 ▲ high +1.17
▼ low -0.96
z mean -0.48 ±0.66 · bl 0.5 · gn 0.2 ▲ high +0.71
▼ low -0.96
Sentence 2
no reference
z mean -0.96 ±0.00 · bl 0.5 · gn 0.1 ▲ high -0.96
▼ low -0.96
z mean -0.75 ±0.42 · bl 0.5 · gn 0.1 ▲ high +0.09
▼ low -0.96
z mean +0.05 ±0.71 · bl 0.6 · gn 0.2 ▲ high +0.88
▼ low -0.87
with emo reference
z mean -0.77 ±0.38 · bl 0.8 · gn 0.3 ▲ high -0.01
▼ low -0.96
z mean -0.72 ±0.38 · bl 0.5 · gn 0.1 ▲ high +0.04
▼ low -0.96
z mean +1.10 ±0.26 · bl 0.6 · gn 0.2 ▲ high +1.36
▼ low +0.60
Sentence 3
no reference
z mean +0.82 ±0.16 · bl 0.1 · gn 0.1 ▲ high +1.01
▼ low +0.62
z mean -0.16 ±0.62 · bl 0.5 · gn 0.1 ▲ high +0.64
▼ low -0.96
z mean +1.23 ±0.23 · bl 0.5 · gn 0.2 ▲ high +1.58
▼ low +0.99
with emo reference
z mean +0.75 ±0.29 · bl 0.2 · gn 0.1 ▲ high +1.13
▼ low +0.23
z mean +0.70 ±0.63 · bl 0.5 · gn 0.1 ▲ high +1.36
▼ low -0.38
z mean +0.96 ±0.31 · bl 0.5 · gn 0.3 ▲ high +1.34
▼ low +0.42
Sentence 4
no reference
z mean -0.96 ±0.00 · bl 0.1 · gn 0.1 ▲ high -0.96
▼ low -0.96
z mean -0.07 ±1.08 · bl 0.3 · gn 0.1 ▲ high +1.36
▼ low -0.96
z mean -0.84 ±0.24 · bl 0.5 · gn 0.2 ▲ high -0.36
▼ low -0.96
with emo reference
z mean -0.70 ±0.28 · bl 0.3 · gn 0.1 ▲ high -0.20
▼ low -0.96
z mean +0.27 ±0.88 · bl 0.6 · gn 0.1 ▲ high +1.32
▼ low -0.83
z mean -0.66 ±0.51 · bl 0.6 · gn 0.2 ▲ high +0.35
▼ low -0.96
Sentence 5
no reference
z mean -0.96 ±0.00 · bl 0.2 · gn 0.1 ▲ high -0.96
▼ low -0.96
z mean -0.96 ±0.00 · bl 0.6 · gn 0.1 ▲ high -0.96
▼ low -0.96
z mean +0.48 ±0.36 · bl 0.6 · gn 0.1 ▲ high +0.95
▼ low -0.04
with emo reference
z mean -0.36 ±0.60 · bl 0.3 · gn 0.2 ▲ high +0.65
▼ low -0.96
z mean -0.05 ±0.85 · bl 0.5 · gn 0.1 ▲ high +1.10
▼ low -0.96
z mean +0.68 ±0.42 · bl 0.6 · gn 0.2 ▲ high +1.14
▼ low -0.05