A cross-modal attention ensemble with balanced stacking reaches MacroF1 0.4094 on 8-class naturalistic speech emotion recognition, beating the official baseline by about 0.08.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model
A cross-modal attention ensemble with balanced stacking reaches MacroF1 0.4094 on 8-class naturalistic speech emotion recognition, beating the official baseline by about 0.08.