← all emotions
Disappointment
Best adapter: rank 16 , checkpoint seen 3336 · EmoNet-z +1.11 (baseline 0.294) · blend 0.536 · genu 0.209 · speaker-sim 0.25.
Instruction prompt: GENERAL: A voice that is adult; extremely carrying chagrin; 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 -1.04 ±0.00 · bl 0.3 · gn 0.1 ▲ high -1.04
▼ low -1.04
z mean +0.13 ±0.63 · bl 0.5 · gn 0.2 ▲ high +0.83
▼ low -1.04
z mean +0.00 ±0.83 · bl 0.6 · gn 0.2 ▲ high +1.01
▼ low -1.04
with emo reference
z mean -0.85 ±0.37 · bl 0.1 · gn 0.3 ▲ high -0.11
▼ low -1.04
z mean -0.02 ±0.54 · bl 0.2 · gn 0.4 ▲ high +0.44
▼ low -1.04
z mean -0.86 ±0.35 · bl 0.2 · gn 0.3 ▲ high -0.16
▼ low -1.04
Sentence 2
no reference
z mean -1.04 ±0.00 · bl 0.5 · gn 0.3 ▲ high -1.04
▼ low -1.04
z mean -1.03 ±0.01 · bl 0.6 · gn 0.2 ▲ high -1.01
▼ low -1.04
z mean -0.77 ±0.54 · bl 0.7 · gn 0.2 ▲ high +0.31
▼ low -1.04
with emo reference
z mean -1.04 ±0.00 · bl 0.4 · gn 0.5 ▲ high -1.04
▼ low -1.04
z mean -0.99 ±0.08 · bl 0.0 · gn 0.4 ▲ high -0.83
▼ low -1.04
z mean -1.04 ±0.00 · bl 0.2 · gn 0.5 ▲ high -1.04
▼ low -1.04
Sentence 3
no reference
z mean -0.85 ±0.37 · bl 0.2 · gn 0.1 ▲ high -0.11
▼ low -1.04
z mean +0.53 ±0.91 · bl 0.5 · gn 0.2 ▲ high +1.31
▼ low -1.04
z mean +0.43 ±0.74 · bl 0.7 · gn 0.3 ▲ high +1.82
▼ low -0.26
with emo reference
z mean -0.18 ±0.46 · bl 0.2 · gn 0.3 ▲ high +0.36
▼ low -1.04
z mean +0.16 ±0.67 · bl 0.1 · gn 0.2 ▲ high +0.94
▼ low -1.04
z mean -0.50 ±0.45 · bl 0.3 · gn 0.5 ▲ high +0.02
▼ low -1.04
Sentence 4
no reference
z mean -0.96 ±0.16 · bl 0.2 · gn 0.1 ▲ high -0.65
▼ low -1.04
z mean -0.71 ±0.59 · bl 0.5 · gn 0.1 ▲ high +0.46
▼ low -1.04
z mean -1.04 ±0.00 · bl 0.6 · gn 0.2 ▲ high -1.04
▼ low -1.04
with emo reference
z mean -0.89 ±0.30 · bl 0.1 · gn 0.2 ▲ high -0.29
▼ low -1.04
z mean +0.14 ±0.73 · bl 0.2 · gn 0.2 ▲ high +1.15
▼ low -1.04
z mean -0.76 ±0.42 · bl 0.3 · gn 0.5 ▲ high +0.04
▼ low -1.04
Sentence 5
no reference
z mean -1.04 ±0.00 · bl 0.2 · gn 0.1 ▲ high -1.04
▼ low -1.04
z mean -0.05 ±0.74 · bl 0.6 · gn 0.2 ▲ high +1.00
▼ low -1.04
z mean -0.36 ±0.84 · bl 0.5 · gn 0.2 ▲ high +0.84
▼ low -1.04
with emo reference
z mean -1.04 ±0.00 · bl 0.2 · gn 0.3 ▲ high -1.04
▼ low -1.04
z mean -0.65 ±0.42 · bl 0.2 · gn 0.4 ▲ high +0.11
▼ low -1.04
z mean -0.78 ±0.51 · bl 0.3 · gn 0.4 ▲ high +0.25
▼ low -1.04